Deep learning in spiking neural networks
In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are...
Saved in:
| Published in | Neural networks Vol. 111; pp. 47 - 63 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Ltd
01.03.2019
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans.
Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and are arguably the only viable option if one wants to understand how the brain computes at the neuronal description level. The spikes of biological neurons are sparse in time and space, and event-driven. Combined with bio-plausible local learning rules, this makes it easier to build low-power, neuromorphic hardware for SNNs. However, training deep SNNs remains a challenge. Spiking neurons’ transfer function is usually non-differentiable, which prevents using backpropagation.
Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy and computational cost. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNNs typically require many fewer operations and are the better candidates to process spatio-temporal data. |
|---|---|
| AbstractList | In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and are arguably the only viable option if one wants to understand how the brain computes at the neuronal description level. The spikes of biological neurons are sparse in time and space, and event-driven. Combined with bio-plausible local learning rules, this makes it easier to build low-power, neuromorphic hardware for SNNs. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy and computational cost. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNNs typically require many fewer operations and are the better candidates to process spatio-temporal data. In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and are arguably the only viable option if one wants to understand how the brain computes at the neuronal description level. The spikes of biological neurons are sparse in time and space, and event-driven. Combined with bio-plausible local learning rules, this makes it easier to build low-power, neuromorphic hardware for SNNs. However, training deep SNNs remains a challenge. Spiking neurons’ transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy and computational cost. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNNs typically require many fewer operations and are the better candidates to process spatio-temporal data. In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and are arguably the only viable option if one wants to understand how the brain computes at the neuronal description level. The spikes of biological neurons are sparse in time and space, and event-driven. Combined with bio-plausible local learning rules, this makes it easier to build low-power, neuromorphic hardware for SNNs. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy and computational cost. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNNs typically require many fewer operations and are the better candidates to process spatio-temporal data.In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained, most often in a supervised manner using backpropagation. Vast amounts of labeled training examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and are arguably the only viable option if one wants to understand how the brain computes at the neuronal description level. The spikes of biological neurons are sparse in time and space, and event-driven. Combined with bio-plausible local learning rules, this makes it easier to build low-power, neuromorphic hardware for SNNs. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy and computational cost. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNNs typically require many fewer operations and are the better candidates to process spatio-temporal data. |
| Author | Kheradpisheh, Saeed Reza Tavanaei, Amirhossein Maida, Anthony Ghodrati, Masoud Masquelier, Timothée |
| Author_xml | – sequence: 1 givenname: Amirhossein orcidid: 0000-0002-6482-440X surname: Tavanaei fullname: Tavanaei, Amirhossein email: tavanaei@louisiana.edu organization: School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA 70504, USA – sequence: 2 givenname: Masoud orcidid: 0000-0002-4006-2578 surname: Ghodrati fullname: Ghodrati, Masoud organization: Department of Physiology, Monash University, Clayton, VIC, Australia – sequence: 3 givenname: Saeed Reza surname: Kheradpisheh fullname: Kheradpisheh, Saeed Reza organization: Department of Computer Science, Faculty of Mathematical Sciences and Computer, Kharazmi University, Tehran, Iran – sequence: 4 givenname: Timothée orcidid: 0000-0001-8629-9506 surname: Masquelier fullname: Masquelier, Timothée organization: CERCO UMR 5549, CNRS-Université de Toulouse 3, F-31300, France – sequence: 5 givenname: Anthony surname: Maida fullname: Maida, Anthony organization: School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA 70504, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30682710$$D View this record in MEDLINE/PubMed https://hal.science/hal-02341924$$DView record in HAL |
| BookMark | eNqFkLtOxDAQRS0EguXxBwhtCUXC-JHEpkBa8ZZWooHacpwJeMk6i50F8fckClBQQDVXo3NvcXbJpm89EnJIIaVA89NF6nHtsUsZUJlSlgKwDTKhslAJKyTbJBOQiic5SNghuzEuACCXgm-THd4HVlCYkONLxNW0QRO8809T56dx5V6G2K8H0_Sne2_DS9wnW7VpIh583T3yeH31cHGbzO9v7i5m88QKobpEiRKh5HWegeGyFmVVVoxJZbMahbKIShouFFMCoBSYZyVmWGWG8hwKVVC-R07G3WfT6FVwSxM-dGucvp3N9fADxgVVTLwN7PHIrkL7usbY6aWLFpvGeGzXUTNaKEFzxlWPHn2h63KJ1c_yt4keOBsBG9oYA9baus50rvVdMK7RFPSgXS_0qF0P2jVlutfel8Wv8vf-P7XzsYa90DeHQUfr0FusXEDb6ap1fw98ArMUm6U |
| CitedBy_id | crossref_primary_10_3389_fncom_2022_859874 crossref_primary_10_1016_j_envsoft_2019_04_012 crossref_primary_10_1016_j_ribaf_2022_101844 crossref_primary_10_1142_S0129065723500442 crossref_primary_10_3389_fncom_2023_1153572 crossref_primary_10_1039_D0NR01671C crossref_primary_10_1007_s00521_023_09293_3 crossref_primary_10_1109_TNNLS_2023_3341446 crossref_primary_10_1016_j_neunet_2022_02_006 crossref_primary_10_1038_s42256_021_00388_x crossref_primary_10_1063_5_0009482 crossref_primary_10_1109_ACCESS_2019_2925085 crossref_primary_10_1002_aisy_202400673 crossref_primary_10_1109_ACCESS_2023_3335387 crossref_primary_10_1002_aisy_202400557 crossref_primary_10_1109_ACCESS_2022_3160271 crossref_primary_10_1016_j_jhydrol_2021_126506 crossref_primary_10_1109_TKDE_2025_3527551 crossref_primary_10_1109_TNNLS_2020_3006263 crossref_primary_10_1360_TB_2023_0775 crossref_primary_10_1109_ACCESS_2020_3037395 crossref_primary_10_18466_cbayarfbe_1538362 crossref_primary_10_1016_j_comnet_2025_111063 crossref_primary_10_1007_s00034_019_01330_8 crossref_primary_10_1016_j_neunet_2025_107333 crossref_primary_10_1007_s00500_020_05501_7 crossref_primary_10_1038_s41467_024_53827_9 crossref_primary_10_1098_rsos_231606 crossref_primary_10_1109_ACCESS_2023_3340735 crossref_primary_10_1109_TBCAS_2022_3166530 crossref_primary_10_1109_ACCESS_2023_3342915 crossref_primary_10_1364_OE_27_037150 crossref_primary_10_1007_s40815_022_01395_9 crossref_primary_10_1007_s10489_024_05629_1 crossref_primary_10_1016_j_array_2023_100323 crossref_primary_10_1364_BOE_531797 crossref_primary_10_1016_j_neunet_2021_08_009 crossref_primary_10_1007_s00521_021_06824_8 crossref_primary_10_1016_j_epsr_2024_111075 crossref_primary_10_1021_acsnano_2c02906 crossref_primary_10_1109_ACCESS_2021_3099492 crossref_primary_10_1109_TASE_2020_3021742 crossref_primary_10_1109_JSEN_2023_3298828 crossref_primary_10_1016_j_neucom_2020_07_105 crossref_primary_10_1007_s11141_022_10175_2 crossref_primary_10_1016_j_commatsci_2022_111835 crossref_primary_10_1021_acsami_4c10687 crossref_primary_10_1080_00207217_2024_2408784 crossref_primary_10_35848_1347_4065_ab8be6 crossref_primary_10_1088_1361_6528_aba70f crossref_primary_10_1016_j_sna_2024_115210 crossref_primary_10_3390_electronics9071059 crossref_primary_10_1055_s_0040_1717824 crossref_primary_10_1007_s11063_021_10680_x crossref_primary_10_1109_TNNLS_2021_3085966 crossref_primary_10_1002_aelm_202200877 crossref_primary_10_1113_JP282755 crossref_primary_10_3389_fncom_2020_00039 crossref_primary_10_1038_s41598_023_50201_5 crossref_primary_10_3390_app10051605 crossref_primary_10_1016_j_neucom_2020_03_079 crossref_primary_10_1109_TED_2022_3159270 crossref_primary_10_1109_TNNLS_2023_3329525 crossref_primary_10_3390_app14178062 crossref_primary_10_1007_s00521_022_06984_1 crossref_primary_10_1109_JBHI_2024_3441332 crossref_primary_10_1109_JSEN_2024_3454153 crossref_primary_10_1109_JSYST_2020_2996185 crossref_primary_10_3389_fnins_2022_991851 crossref_primary_10_1007_s11263_024_02046_2 crossref_primary_10_1109_ACCESS_2024_3444596 crossref_primary_10_1007_s11831_023_09901_4 crossref_primary_10_1063_5_0152703 crossref_primary_10_1016_j_heliyon_2022_e08803 crossref_primary_10_1021_acs_nanolett_3c01597 crossref_primary_10_1039_D3TC04265K crossref_primary_10_1109_ACCESS_2020_3001296 crossref_primary_10_3389_fnsys_2022_838822 crossref_primary_10_1038_s43588_024_00674_9 crossref_primary_10_1109_TDSC_2022_3148331 crossref_primary_10_3390_cryptography7020017 crossref_primary_10_1016_j_neucom_2024_128173 crossref_primary_10_1109_ACCESS_2020_3040895 crossref_primary_10_1088_1757_899X_873_1_012019 crossref_primary_10_1007_s11071_024_09525_8 crossref_primary_10_1016_j_aei_2025_103132 crossref_primary_10_1109_TCAD_2020_3013049 crossref_primary_10_1109_MIC_2023_3301010 crossref_primary_10_35848_1347_4065_ac5533 crossref_primary_10_3389_fnins_2023_1225871 crossref_primary_10_1109_MED_2023_3296084 crossref_primary_10_1016_j_neucom_2023_126838 crossref_primary_10_1103_PhysRevLett_125_207202 crossref_primary_10_1109_TCASAI_2025_3532406 crossref_primary_10_3389_fphys_2024_1379977 crossref_primary_10_3389_fnbot_2020_568319 crossref_primary_10_1038_s41598_024_84775_5 crossref_primary_10_1007_s10489_023_04966_x crossref_primary_10_1007_s11063_021_10669_6 crossref_primary_10_1109_MCAS_2022_3142669 crossref_primary_10_1109_TETCI_2024_3363071 crossref_primary_10_1088_2634_4386_ac1a64 crossref_primary_10_1016_j_neucom_2024_128190 crossref_primary_10_1109_TNNLS_2023_3329741 crossref_primary_10_1155_2022_4134864 crossref_primary_10_1088_2634_4386_ac4c38 crossref_primary_10_1021_acsnano_4c07454 crossref_primary_10_1109_LED_2021_3138907 crossref_primary_10_1016_j_neunet_2019_09_024 crossref_primary_10_1186_s42234_021_00078_4 crossref_primary_10_1016_j_neucom_2020_01_109 crossref_primary_10_1038_s41467_024_48905_x crossref_primary_10_1007_s12274_023_5639_5 crossref_primary_10_1016_j_optcom_2024_130374 crossref_primary_10_1016_j_neucom_2020_07_109 crossref_primary_10_3389_fnins_2019_00625 crossref_primary_10_1016_j_neucom_2021_09_004 crossref_primary_10_1016_j_neunet_2021_07_011 crossref_primary_10_1063_5_0066350 crossref_primary_10_1016_j_neunet_2019_09_026 crossref_primary_10_1016_j_neucom_2022_06_036 crossref_primary_10_1063_5_0204469 crossref_primary_10_1109_TCDS_2023_3278712 crossref_primary_10_1109_TIP_2023_3249579 crossref_primary_10_1016_j_mtphys_2022_100667 crossref_primary_10_1109_TBCAS_2023_3292469 crossref_primary_10_3390_brainsci13020168 crossref_primary_10_1088_2634_4386_adb884 crossref_primary_10_1021_acssensors_4c01867 crossref_primary_10_1016_j_matpr_2021_10_088 crossref_primary_10_1109_TBCAS_2023_3327496 crossref_primary_10_1108_IJICC_06_2020_0061 crossref_primary_10_1109_JPROC_2024_3429360 crossref_primary_10_1016_j_isatra_2023_06_008 crossref_primary_10_3390_electronics11121889 crossref_primary_10_3389_fnbot_2024_1395617 crossref_primary_10_1038_s41524_021_00564_y crossref_primary_10_3390_e26020126 crossref_primary_10_3389_frobt_2022_1007547 crossref_primary_10_3390_brainsci12020281 crossref_primary_10_1103_PhysRevApplied_14_014096 crossref_primary_10_1142_S0219649222500174 crossref_primary_10_1109_TBCAS_2024_3389875 crossref_primary_10_3390_biomimetics9100646 crossref_primary_10_1109_TNNLS_2021_3095724 crossref_primary_10_1109_ACCESS_2023_3236800 crossref_primary_10_1109_ACCESS_2024_3391889 crossref_primary_10_7554_eLife_86365 crossref_primary_10_1016_j_neunet_2022_09_003 crossref_primary_10_1016_j_displa_2024_102864 crossref_primary_10_1016_j_patrec_2022_01_008 crossref_primary_10_1109_TNNLS_2020_3044364 crossref_primary_10_3389_fncom_2024_1363514 crossref_primary_10_1002_dac_70035 crossref_primary_10_3390_math11071701 crossref_primary_10_3390_mi15040426 crossref_primary_10_1016_j_tcs_2020_07_016 crossref_primary_10_1371_journal_pone_0244683 crossref_primary_10_1007_s12555_019_0403_z crossref_primary_10_1002_admt_202401316 crossref_primary_10_1109_TCSVT_2023_3272375 crossref_primary_10_1109_JETCAS_2023_3328863 crossref_primary_10_1109_TCSI_2021_3052885 crossref_primary_10_1108_IJPCC_02_2021_0037 crossref_primary_10_1002_cta_2753 crossref_primary_10_1016_j_cscm_2023_e02800 crossref_primary_10_1007_s11432_023_3789_7 crossref_primary_10_1109_ACCESS_2022_3221123 crossref_primary_10_1016_j_neucom_2021_11_097 crossref_primary_10_1109_TCSII_2020_2997117 crossref_primary_10_1016_j_neucom_2023_126988 crossref_primary_10_3390_e24040455 crossref_primary_10_1080_03772063_2024_2378475 crossref_primary_10_1088_2632_2153_ada220 crossref_primary_10_1007_s11063_023_11247_8 crossref_primary_10_1142_S0218126625500987 crossref_primary_10_3389_fninf_2023_941696 crossref_primary_10_1155_2021_9290921 crossref_primary_10_1109_TED_2023_3324898 crossref_primary_10_3389_fnins_2024_1449020 crossref_primary_10_1016_j_mtcomm_2024_109675 crossref_primary_10_1109_TWC_2021_3123220 crossref_primary_10_1109_LED_2024_3445970 crossref_primary_10_1016_j_measurement_2023_113273 crossref_primary_10_1109_MC_2024_3437828 crossref_primary_10_3389_fncom_2019_00055 crossref_primary_10_1109_TC_2022_3197089 crossref_primary_10_1038_s44172_024_00165_9 crossref_primary_10_1142_S0218127423501328 crossref_primary_10_1002_adma_202204778 crossref_primary_10_1088_1361_6528_ac0ac4 crossref_primary_10_1109_JSTARS_2023_3242310 crossref_primary_10_1007_s12559_023_10113_y crossref_primary_10_1016_j_neucom_2023_126784 crossref_primary_10_1371_journal_pcbi_1011005 crossref_primary_10_1063_5_0129205 crossref_primary_10_1126_scirobotics_adi0591 crossref_primary_10_1088_2634_4386_acc683 crossref_primary_10_3390_ma13040938 crossref_primary_10_1038_s41598_022_17013_5 crossref_primary_10_1088_1674_1056_ad1c58 crossref_primary_10_1109_TED_2023_3236906 crossref_primary_10_1007_s11042_020_10243_7 crossref_primary_10_1016_j_neunet_2024_106474 crossref_primary_10_1016_j_ress_2023_109102 crossref_primary_10_1587_transinf_2022EDP7183 crossref_primary_10_3390_biomimetics7040246 crossref_primary_10_1016_j_knosys_2020_105472 crossref_primary_10_1007_s00521_022_07513_w crossref_primary_10_1109_TNSM_2022_3169988 crossref_primary_10_1007_s11063_021_10562_2 crossref_primary_10_3389_fninf_2023_1067095 crossref_primary_10_3390_math10183275 crossref_primary_10_1016_j_cageo_2025_105864 crossref_primary_10_1021_acsaelm_4c00482 crossref_primary_10_1109_TCASAI_2024_3496837 crossref_primary_10_1109_TBCAS_2022_3209073 crossref_primary_10_1021_acsami_3c12244 crossref_primary_10_3390_sym14030505 crossref_primary_10_1016_j_neunet_2024_106244 crossref_primary_10_1109_TIP_2024_3430080 crossref_primary_10_1016_j_neunet_2024_106368 crossref_primary_10_1109_TCYB_2022_3188015 crossref_primary_10_1038_s41598_020_64878_5 crossref_primary_10_3389_fnins_2021_638474 crossref_primary_10_1016_j_mjafi_2020_10_005 crossref_primary_10_1021_acsaelm_3c01323 crossref_primary_10_1109_JSTQE_2020_3005589 crossref_primary_10_3389_fnins_2024_1439155 crossref_primary_10_1109_TCSI_2024_3352729 crossref_primary_10_3390_math12081230 crossref_primary_10_1016_j_neucom_2021_02_027 crossref_primary_10_1109_TCDS_2021_3073846 crossref_primary_10_1177_10943420231178537 crossref_primary_10_1109_ACCESS_2022_3213816 crossref_primary_10_3389_fnins_2023_994517 crossref_primary_10_1109_TETCI_2024_3359539 crossref_primary_10_1002_aisy_202100054 crossref_primary_10_1038_s43588_021_00132_w crossref_primary_10_3389_fnbot_2023_1149675 crossref_primary_10_1002_adma_202108025 crossref_primary_10_3389_fnins_2022_819063 crossref_primary_10_3389_fnins_2023_1209795 crossref_primary_10_1080_14680629_2023_2230298 crossref_primary_10_1016_j_asoc_2019_04_006 crossref_primary_10_3390_math9243237 crossref_primary_10_1016_j_neucom_2024_127934 crossref_primary_10_1063_5_0243083 crossref_primary_10_1038_s41598_023_42605_0 crossref_primary_10_3389_fncom_2023_1215824 crossref_primary_10_1016_j_procs_2021_09_280 crossref_primary_10_1109_ACCESS_2024_3445464 crossref_primary_10_1109_TNNLS_2020_3005538 crossref_primary_10_3389_fnbot_2022_817948 crossref_primary_10_3390_bdcc7020110 crossref_primary_10_1109_ACCESS_2024_3365632 crossref_primary_10_3390_s22228845 crossref_primary_10_1016_j_image_2025_117263 crossref_primary_10_1109_TBME_2024_3498097 crossref_primary_10_3390_info14100537 crossref_primary_10_3389_fncom_2024_1338280 crossref_primary_10_3389_fnins_2022_949142 crossref_primary_10_3390_brainsci10110781 crossref_primary_10_1016_j_physa_2023_129334 crossref_primary_10_1109_TCDS_2021_3140115 crossref_primary_10_1109_ACCESS_2023_3249966 crossref_primary_10_1145_3635032 crossref_primary_10_3389_fnins_2022_1018006 crossref_primary_10_25726_v0077_0284_6922_y crossref_primary_10_1109_TNNLS_2023_3263008 crossref_primary_10_1145_3520133 crossref_primary_10_1088_1757_899X_890_1_012144 crossref_primary_10_1109_ACCESS_2025_3551270 crossref_primary_10_1016_j_neucom_2024_127953 crossref_primary_10_7717_peerj_cs_2549 crossref_primary_10_1016_j_softx_2024_102006 crossref_primary_10_1109_MNANO_2021_3098219 crossref_primary_10_3389_fnins_2022_838832 crossref_primary_10_3390_electronics13071281 crossref_primary_10_1016_j_neunet_2023_09_011 crossref_primary_10_1002_aisy_202100159 crossref_primary_10_1177_14759217241305159 crossref_primary_10_3390_s21093240 crossref_primary_10_1016_j_knosys_2024_111816 crossref_primary_10_1038_s41598_023_27385_x crossref_primary_10_1145_3451214 crossref_primary_10_1109_TNNLS_2023_3285488 crossref_primary_10_1109_TNNLS_2023_3286458 crossref_primary_10_1016_j_ins_2022_04_054 crossref_primary_10_1371_journal_pcbi_1011315 crossref_primary_10_3390_agronomy15010242 crossref_primary_10_7498_aps_72_20230819 crossref_primary_10_1002_aelm_202100465 crossref_primary_10_3390_electronics8121479 crossref_primary_10_1007_s11571_024_10133_w crossref_primary_10_3390_medicina56070364 crossref_primary_10_7566_JPSJ_90_074802 crossref_primary_10_1016_j_neucom_2021_10_080 crossref_primary_10_1109_TIP_2021_3122092 crossref_primary_10_1109_JEDS_2021_3057456 crossref_primary_10_1002_ett_4169 crossref_primary_10_1038_s41928_021_00705_7 crossref_primary_10_1109_TSIPI_2022_3222122 crossref_primary_10_3390_polym14173668 crossref_primary_10_1002_adma_202003610 crossref_primary_10_1177_02783649241284058 crossref_primary_10_1016_j_tcs_2022_09_021 crossref_primary_10_1109_LRA_2020_3012129 crossref_primary_10_3389_fnins_2023_1093865 crossref_primary_10_1109_JETCAS_2022_3224071 crossref_primary_10_3390_sci4040046 crossref_primary_10_1038_s41467_022_32884_y crossref_primary_10_3389_fnins_2022_945037 crossref_primary_10_1063_5_0133515 crossref_primary_10_1109_ACCESS_2021_3094262 crossref_primary_10_1007_s00521_021_05832_y crossref_primary_10_1007_s00521_020_05388_3 crossref_primary_10_1002_aisy_202300383 crossref_primary_10_1109_TCDS_2024_3422873 crossref_primary_10_1103_PhysRevResearch_3_023146 crossref_primary_10_1007_s13369_020_04872_1 crossref_primary_10_1002_adma_201902761 crossref_primary_10_1109_TBCAS_2023_3268502 crossref_primary_10_2174_0129503779282967240315040931 crossref_primary_10_3390_make5030052 crossref_primary_10_1016_j_neunet_2022_06_001 crossref_primary_10_1088_2634_4386_ad473b crossref_primary_10_1088_2634_4386_ad6cef crossref_primary_10_1016_j_neucom_2024_128707 crossref_primary_10_1016_j_neucom_2023_126234 crossref_primary_10_1109_TED_2021_3098503 crossref_primary_10_3389_frai_2022_680165 crossref_primary_10_1016_j_neucom_2022_01_021 crossref_primary_10_1002_aisy_202300136 crossref_primary_10_1007_s11042_023_16344_3 crossref_primary_10_1016_j_neunet_2019_06_001 crossref_primary_10_1109_ACCESS_2020_3047993 crossref_primary_10_3389_fnins_2023_1159440 crossref_primary_10_1109_TNSRE_2023_3336467 crossref_primary_10_1002_aisy_202300132 crossref_primary_10_1016_j_asoc_2020_106691 crossref_primary_10_1109_TETC_2024_3387026 crossref_primary_10_3390_s23167232 crossref_primary_10_1016_j_jjimei_2024_100286 crossref_primary_10_1109_TCSII_2024_3485178 crossref_primary_10_1016_j_avb_2020_101536 crossref_primary_10_1007_s10489_023_04553_0 crossref_primary_10_1038_s41467_021_24427_8 crossref_primary_10_1007_s11571_022_09799_x crossref_primary_10_3389_fnano_2021_801999 crossref_primary_10_3390_s23146578 crossref_primary_10_1007_s11276_021_02555_9 crossref_primary_10_1016_j_measurement_2023_113796 crossref_primary_10_1109_ACCESS_2020_3034353 crossref_primary_10_1109_ACCESS_2025_3544379 crossref_primary_10_1038_s41598_021_91786_z crossref_primary_10_1109_TCYB_2022_3227363 crossref_primary_10_1016_j_neunet_2020_02_010 crossref_primary_10_1021_acsaelm_4c02015 crossref_primary_10_1016_j_neunet_2020_02_011 crossref_primary_10_1109_TCDS_2023_3338614 crossref_primary_10_1109_ACCESS_2021_3094484 crossref_primary_10_1142_S0129065720500276 crossref_primary_10_3389_fnins_2022_857513 crossref_primary_10_3390_app13084809 crossref_primary_10_1016_j_flatc_2024_100755 crossref_primary_10_1021_acsnano_4c12884 crossref_primary_10_1109_TCDS_2024_3406168 crossref_primary_10_3389_fdata_2022_787421 crossref_primary_10_1103_PhysRevResearch_4_043051 crossref_primary_10_3389_fnins_2023_1270090 crossref_primary_10_1162_neco_a_01424 crossref_primary_10_1162_neco_a_01668 crossref_primary_10_1038_s41598_020_69361_9 crossref_primary_10_1002_jnm_3227 crossref_primary_10_1038_s44287_024_00107_9 crossref_primary_10_1016_j_neucom_2023_126377 crossref_primary_10_1002_aelm_202400421 crossref_primary_10_3389_fmats_2023_1269992 crossref_primary_10_1109_TC_2024_3416705 crossref_primary_10_1021_acsomega_4c10277 crossref_primary_10_1007_s42979_022_01259_x crossref_primary_10_1016_j_compeleceng_2024_109562 crossref_primary_10_1109_ACCESS_2020_2998098 crossref_primary_10_1016_j_neunet_2023_01_026 crossref_primary_10_1016_j_energy_2020_117072 crossref_primary_10_1016_j_robot_2024_104782 crossref_primary_10_1103_PhysRevApplied_19_064010 crossref_primary_10_1109_TED_2022_3207707 crossref_primary_10_1109_TCSI_2021_3066967 crossref_primary_10_3389_fnins_2021_629000 crossref_primary_10_1088_2634_4386_ac7c8a crossref_primary_10_1002_adma_202208683 crossref_primary_10_1038_s41467_021_22576_4 crossref_primary_10_3390_pr11092772 crossref_primary_10_1016_j_cosrev_2020_100288 crossref_primary_10_1002_aelm_202300904 crossref_primary_10_3389_fncom_2022_1054421 crossref_primary_10_1142_S0129065724500345 crossref_primary_10_34133_icomputing_0032 crossref_primary_10_1109_JPHOT_2024_3361930 crossref_primary_10_1109_JSEN_2024_3520666 crossref_primary_10_1088_2634_4386_ac7a5a crossref_primary_10_3390_e27030267 crossref_primary_10_1016_j_neuron_2020_09_005 crossref_primary_10_1371_journal_pone_0252676 crossref_primary_10_3390_en15197256 crossref_primary_10_3389_fnins_2021_694170 crossref_primary_10_1007_s13534_024_00406_y crossref_primary_10_1016_j_carpta_2024_100627 crossref_primary_10_1016_j_jmapro_2024_11_066 crossref_primary_10_1162_neco_a_01409 crossref_primary_10_30931_jetas_1432261 crossref_primary_10_1049_bme2_12099 crossref_primary_10_1145_3461667 crossref_primary_10_18034_ajase_v10i1_17 crossref_primary_10_1016_j_rser_2023_113728 crossref_primary_10_1016_j_chaos_2024_115940 crossref_primary_10_1109_ACCESS_2020_2995886 crossref_primary_10_1109_TNNLS_2021_3110991 crossref_primary_10_1145_3510854 crossref_primary_10_1109_TCSI_2020_3027583 crossref_primary_10_1109_TCSII_2021_3063784 crossref_primary_10_1016_j_neunet_2020_01_017 crossref_primary_10_3389_fnins_2022_937782 crossref_primary_10_1088_2634_4386_adb7fe crossref_primary_10_23919_emsci_2023_0015 crossref_primary_10_1063_5_0179424 crossref_primary_10_1109_TVLSI_2023_3335232 crossref_primary_10_3390_jlpea12040059 crossref_primary_10_1016_j_chip_2024_100093 crossref_primary_10_1016_j_neunet_2024_106318 crossref_primary_10_1109_ACCESS_2020_2985839 crossref_primary_10_1109_JPROC_2020_3045625 crossref_primary_10_1109_TNNLS_2021_3095068 crossref_primary_10_1016_j_icte_2020_05_002 crossref_primary_10_1080_02664763_2024_2395961 crossref_primary_10_1080_10298436_2023_2257852 crossref_primary_10_1109_COMST_2024_3365076 crossref_primary_10_1109_JETCAS_2023_3328926 crossref_primary_10_1063_5_0210790 crossref_primary_10_1016_j_neucom_2024_127792 crossref_primary_10_1117_1_NPh_11_3_033405 crossref_primary_10_1007_s11063_023_11348_4 crossref_primary_10_1109_TVT_2020_3022394 crossref_primary_10_1016_j_knosys_2024_112627 crossref_primary_10_1063_1_5129306 crossref_primary_10_1007_s13534_024_00404_0 crossref_primary_10_1109_ACCESS_2020_2981346 crossref_primary_10_1007_s12559_022_09994_2 crossref_primary_10_1007_s11042_022_12624_6 crossref_primary_10_3389_fphy_2024_1334298 crossref_primary_10_1021_acs_chemrev_4c00369 crossref_primary_10_1063_5_0193810 crossref_primary_10_1002_adma_202412549 crossref_primary_10_1109_TCSVT_2024_3495769 crossref_primary_10_1002_aisy_202400282 crossref_primary_10_1007_s00521_023_08672_0 crossref_primary_10_1002_adfm_202405670 crossref_primary_10_1016_j_neucom_2024_128650 crossref_primary_10_1016_j_orgel_2022_106455 crossref_primary_10_1049_ipr2_12437 crossref_primary_10_1016_j_sse_2022_108481 crossref_primary_10_1103_PhysRevApplied_23_034051 crossref_primary_10_1038_s41598_023_31365_6 crossref_primary_10_1109_ACCESS_2020_3041946 crossref_primary_10_3233_AIC_210009 crossref_primary_10_1016_j_engappai_2024_109756 crossref_primary_10_1109_TASE_2024_3359641 crossref_primary_10_1109_ACCESS_2025_3548318 crossref_primary_10_3389_frai_2022_770254 crossref_primary_10_1109_TASLP_2022_3221011 crossref_primary_10_1038_s41598_020_60572_8 crossref_primary_10_1016_j_nhres_2023_10_001 crossref_primary_10_1016_j_neucom_2020_07_047 crossref_primary_10_1002_smll_202000041 crossref_primary_10_1155_2020_9464593 crossref_primary_10_1063_5_0026093 crossref_primary_10_1016_j_jcp_2024_113363 crossref_primary_10_1109_TCE_2023_3279135 crossref_primary_10_1016_j_eng_2020_02_004 crossref_primary_10_1109_TNNLS_2024_3353571 crossref_primary_10_1162_neco_a_01604 crossref_primary_10_1007_s11071_019_05309_7 crossref_primary_10_1109_ACCESS_2025_3544086 crossref_primary_10_1109_MSP_2019_2931595 crossref_primary_10_3389_fncom_2022_1017284 crossref_primary_10_1016_j_compind_2019_103132 crossref_primary_10_3390_info15080472 crossref_primary_10_35848_1347_4065_ad53b2 crossref_primary_10_1007_s00371_021_02237_9 crossref_primary_10_3390_brainsci14111149 crossref_primary_10_1109_ACCESS_2024_3479968 crossref_primary_10_1109_TIM_2025_3547517 crossref_primary_10_1098_rsta_2018_0131 crossref_primary_10_3389_fnins_2023_1233037 crossref_primary_10_3389_fninf_2021_715131 crossref_primary_10_1016_j_engappai_2024_109415 crossref_primary_10_1016_j_neunet_2019_09_036 crossref_primary_10_1038_s41467_024_51254_4 crossref_primary_10_1038_s41928_022_00876_x crossref_primary_10_1016_j_autcon_2024_105723 crossref_primary_10_1088_1361_6668_ad44e3 crossref_primary_10_1109_TCAD_2021_3120068 crossref_primary_10_1038_s41598_018_35828_z crossref_primary_10_1007_s00339_022_06365_4 crossref_primary_10_1007_s10489_023_04921_w crossref_primary_10_1109_LES_2023_3328223 crossref_primary_10_1021_acs_nanolett_8b04023 crossref_primary_10_1109_ACCESS_2020_2990416 crossref_primary_10_1038_s41928_022_00840_9 crossref_primary_10_1016_j_eswa_2022_116570 crossref_primary_10_1016_j_neunet_2019_08_019 crossref_primary_10_1162_neco_a_01702 crossref_primary_10_1002_adma_202306818 crossref_primary_10_1002_aisy_202200179 crossref_primary_10_1109_TNNLS_2021_3071976 crossref_primary_10_1063_5_0047946 crossref_primary_10_3390_s24113426 crossref_primary_10_1016_j_neunet_2021_09_021 crossref_primary_10_1134_S105261882307004X crossref_primary_10_1242_jeb_245409 crossref_primary_10_1007_s00422_024_00998_9 crossref_primary_10_1002_er_4855 crossref_primary_10_1016_j_neucom_2025_129440 crossref_primary_10_3389_fnins_2023_1047008 crossref_primary_10_1063_5_0158341 crossref_primary_10_1021_acsomega_3c09936 crossref_primary_10_3748_wjg_v25_i14_1666 crossref_primary_10_1109_TCSII_2023_3301180 crossref_primary_10_1016_j_marmicro_2023_102293 crossref_primary_10_1016_j_tbench_2023_100108 crossref_primary_10_1016_j_neunet_2024_106976 crossref_primary_10_1371_journal_pone_0204596 crossref_primary_10_3389_fnins_2020_00199 crossref_primary_10_1007_s11263_024_02148_x crossref_primary_10_1016_j_ijhydene_2024_03_115 crossref_primary_10_1016_j_neucom_2023_02_026 crossref_primary_10_1109_TNANO_2024_3505985 crossref_primary_10_1109_TNNLS_2021_3082911 crossref_primary_10_1109_ACCESS_2022_3187033 crossref_primary_10_3390_electronics8101065 crossref_primary_10_1038_s41467_022_30964_7 crossref_primary_10_1080_14686996_2023_2188878 crossref_primary_10_1126_sciadv_adi1480 crossref_primary_10_1063_5_0191571 crossref_primary_10_1016_j_neucom_2021_05_104 crossref_primary_10_1002_pssr_202300181 crossref_primary_10_1109_TCAD_2022_3197512 crossref_primary_10_3390_brainsci15030217 crossref_primary_10_3389_fnbot_2020_589532 crossref_primary_10_1109_JSEN_2023_3329559 crossref_primary_10_1109_TED_2021_3077346 crossref_primary_10_3389_fnins_2020_00088 crossref_primary_10_1007_s40747_023_01333_8 crossref_primary_10_1061_JSDCCC_SCENG_1611 crossref_primary_10_1016_j_ress_2023_109850 crossref_primary_10_1007_s13748_024_00313_4 crossref_primary_10_1109_TNNLS_2020_3043415 crossref_primary_10_3389_fnins_2024_1291053 crossref_primary_10_1016_j_rineng_2023_100984 crossref_primary_10_3390_electronics13050909 crossref_primary_10_1016_j_amc_2022_127630 crossref_primary_10_3389_fncom_2023_1274575 crossref_primary_10_1002_adma_202303336 crossref_primary_10_3389_fphy_2022_839243 crossref_primary_10_1007_s10489_022_04258_w crossref_primary_10_1016_j_mattod_2022_08_017 crossref_primary_10_3390_nano14171412 crossref_primary_10_1038_s41598_024_59469_7 crossref_primary_10_1109_TNNLS_2023_3278265 crossref_primary_10_1016_j_neunet_2023_05_038 crossref_primary_10_1063_5_0126890 crossref_primary_10_1063_5_0191119 crossref_primary_10_1016_j_procs_2025_01_025 crossref_primary_10_1016_j_vlsi_2023_04_002 crossref_primary_10_3390_electronics13152988 crossref_primary_10_1021_acsphotonics_2c01516 crossref_primary_10_1016_j_engappai_2024_109845 crossref_primary_10_1038_s41578_019_0159_3 crossref_primary_10_1109_ACCESS_2024_3389288 crossref_primary_10_1109_TED_2020_3017186 crossref_primary_10_1002_adfm_202113050 crossref_primary_10_17798_bitlisfen_1024236 crossref_primary_10_1007_s12293_022_00373_w crossref_primary_10_1038_s41598_023_35005_x crossref_primary_10_3389_fnins_2022_999029 crossref_primary_10_3390_electronics10182281 crossref_primary_10_1016_j_ress_2022_108561 crossref_primary_10_1088_2634_4386_ad4411 crossref_primary_10_1016_j_neucom_2020_11_016 |
| Cites_doi | 10.1038/nature04050 10.1007/s13218-012-0204-5 10.1109/72.991428 10.1207/s15516709cog1402_1 10.1073/pnas.79.8.2554 10.1016/j.neucom.2004.01.068 10.1109/TNNLS.2014.2362542 10.1109/CVPR.2016.308 10.1023/B:NACO.0000027755.02868.60 10.1016/j.cosrev.2009.03.005 10.1007/BF02331346 10.1109/ICRC.2016.7738691 10.1146/annurev.neuro.31.060407.125639 10.1162/neco.2007.19.6.1437 10.1016/S0925-2312(99)00095-8 10.1038/nn1643 10.1016/j.neucom.2013.06.052 10.1007/s11263-014-0788-3 10.1371/journal.pcbi.1004566 10.1162/neco.2009.11-08-901 10.1016/j.ipl.2005.05.023 10.1007/s11063-010-9149-6 10.1016/j.specom.2008.08.002 10.1109/5.726791 10.1073/pnas.1611734114 10.1109/CVPR.2015.7298965 10.1080/03640210802353016 10.1561/2200000006 10.3389/fnins.2017.00350 10.1162/neco.1997.9.5.1015 10.1109/CVPR.2014.222 10.1109/MSP.2012.2205597 10.1016/j.neunet.2013.07.012 10.1016/j.neucom.2013.09.049 10.1113/jphysiol.1959.sp006308 10.1145/2001269.2001295 10.1109/TVLSI.2013.2294916 10.3389/fnins.2015.00222 10.1162/0899766053429390 10.1162/neco_a_01086 10.1113/jphysiol.1952.sp004764 10.1109/TCAD.2015.2474396 10.1016/S0042-6989(97)00121-1 10.1214/aoms/1177729694 10.1038/nature06105 10.1038/34584 10.1016/j.neucom.2014.04.017 10.3233/ICA-2007-14301 10.1371/journal.pcbi.1003037 10.1103/PhysRevLett.118.018103 10.1016/j.neucom.2013.03.047 10.1016/S0896-6273(03)00761-X 10.1109/TPAMI.2016.2574707 10.1016/S0925-2312(02)00494-0 10.1007/s11263-015-0816-y 10.1371/journal.pcbi.1002250 10.1109/JPROC.2015.2496679 10.1016/S0925-2312(01)00658-0 10.1016/j.conb.2005.08.002 10.1016/j.neunet.2014.09.003 10.1523/JNEUROSCI.20-14-05392.2000 10.1093/nar/gkw226 10.3389/fnins.2015.00437 10.1162/neco.2006.18.7.1527 10.1093/bioinformatics/btw255 10.1016/j.neunet.2014.01.006 10.1073/pnas.1604850113 10.1016/j.neunet.2009.04.003 10.14569/IJARAI.2015.040701 10.1016/j.neucom.2017.01.088 10.1038/srep32672 10.1016/j.neunet.2012.11.014 10.1162/NECO_a_00934 10.1016/j.neunet.2010.04.009 10.3389/fpsyg.2017.00142 10.1103/PhysRevE.96.042156 10.1007/s10827-006-0003-9 10.1162/neco.2006.18.6.1318 10.1371/journal.pone.0040233 10.1016/j.neucom.2012.08.034 10.1088/0954-898X_8_2_003 10.1126/science.1194908 10.1038/nature14539 10.1109/CVPR.2016.90 10.3389/fnsyn.2011.00004 10.1364/JOSA.70.001297 10.1109/CVPR.2014.81 10.1109/TASL.2011.2109382 10.1523/JNEUROSCI.5044-12.2013 10.1109/TNNLS.2017.2726060 10.1142/S0129065709002002 10.1038/376033a0 10.1109/72.279181 10.1109/TPAMI.2013.71 10.1103/PhysRevLett.118.138301 10.1152/physrev.00030.2005 10.1016/j.neunet.2012.04.004 10.1038/78829 10.1038/nature02169 10.1371/journal.pcbi.1003511 10.1113/jphysiol.1962.sp006837 10.1371/journal.pcbi.1002211 10.1126/science.7770778 10.1523/JNEUROSCI.1425-06.2006 10.3389/fncom.2016.00092 10.1016/j.neunet.2017.12.005 10.1162/neco.2007.19.11.2881 10.1093/cercor/1.1.1 10.1162/neco_a_00990 10.1162/089976602760407955 10.1038/s41598-018-27169-8 10.1162/neco.2008.04-07-510 10.1007/BF00229331 10.1126/science.1254642 10.1162/neco.1996.8.1.1 10.1371/journal.pone.0001377 10.1162/neco.1997.9.8.1735 10.1109/CVPR.2014.233 10.1371/journal.pcbi.1000757 10.1007/s11263-008-0201-1 10.1162/neco.1996.8.6.1185 10.1523/JNEUROSCI.5153-10.2011 10.3389/fnins.2016.00508 10.1162/neco.2008.06-08-804 10.1038/381607a0 10.1016/j.ins.2012.07.023 10.1016/j.neuron.2017.06.011 10.1109/TNN.2003.820440 10.1162/neco.2010.08-09-1081 10.1109/TPDS.2012.289 10.1016/S0893-6080(97)00011-7 10.1523/JNEUROSCI.4188-12.2013 10.1142/S0129065712500128 10.1126/science.1149639 10.3389/fncom.2018.00046 10.3389/fncom.2018.00042 10.1021/acs.molpharmaceut.5b00982 10.1126/science.1225266 10.3389/fncom.2015.00099 10.1016/j.neucom.2016.04.029 10.1007/s11265-016-1153-2 10.1016/j.neunet.2018.05.018 10.1109/TNANO.2013.2250995 10.1371/journal.pcbi.0030031 10.1016/j.neucom.2007.12.038 10.1016/j.cell.2017.01.005 10.1016/j.neunet.2012.06.003 10.3389/fnins.2017.00324 10.3389/fnins.2017.00682 10.1371/journal.pbio.1002018 10.1038/srep17573 10.1103/PhysRevE.97.022310 10.1109/TNN.2010.2074212 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier Ltd Copyright © 2018 Elsevier Ltd. All rights reserved. Distributed under a Creative Commons Attribution 4.0 International License |
| Copyright_xml | – notice: 2018 Elsevier Ltd – notice: Copyright © 2018 Elsevier Ltd. All rights reserved. – notice: Distributed under a Creative Commons Attribution 4.0 International License |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 1XC VOOES |
| DOI | 10.1016/j.neunet.2018.12.002 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 63 |
| ExternalDocumentID | oai_HAL_hal_02341924v1 30682710 10_1016_j_neunet_2018_12_002 S0893608018303332 |
| Genre | Journal Article Review |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH CGR CUY CVF ECM EIF NPM PKN 7X8 1XC EFKBS VOOES |
| ID | FETCH-LOGICAL-c449t-94be0b3f650a38f4bdbd2289c5fe49cee98a34929400b4e65be5ed5a136079713 |
| IEDL.DBID | .~1 |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Fri Jul 25 06:45:03 EDT 2025 Fri Jul 11 14:59:00 EDT 2025 Wed Feb 19 02:37:07 EST 2025 Tue Jul 01 01:24:33 EDT 2025 Thu Apr 24 23:08:42 EDT 2025 Fri Feb 23 02:28:37 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Spiking neural network Power-efficient architecture Machine learning Biological plausibility |
| Language | English |
| License | Copyright © 2018 Elsevier Ltd. All rights reserved. Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c449t-94be0b3f650a38f4bdbd2289c5fe49cee98a34929400b4e65be5ed5a136079713 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 ObjectType-Review-3 content type line 23 |
| ORCID | 0000-0002-4006-2578 0000-0001-8629-9506 0000-0002-6482-440X 0000-0001-6168-4379 |
| OpenAccessLink | https://hal.science/hal-02341924 |
| PMID | 30682710 |
| PQID | 2179416239 |
| PQPubID | 23479 |
| PageCount | 17 |
| ParticipantIDs | hal_primary_oai_HAL_hal_02341924v1 proquest_miscellaneous_2179416239 pubmed_primary_30682710 crossref_citationtrail_10_1016_j_neunet_2018_12_002 crossref_primary_10_1016_j_neunet_2018_12_002 elsevier_sciencedirect_doi_10_1016_j_neunet_2018_12_002 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2019-03-01 |
| PublicationDateYYYYMMDD | 2019-03-01 |
| PublicationDate_xml | – month: 03 year: 2019 text: 2019-03-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2019 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Paulun, Wendt, Kasabov (b175) 2018; 12 Bengio, Simard, Frasconi (b14) 1994; 5 Bengio (b11) 2009; 2 Neil, D., Pfeiffer, M., & Liu, S. (2016a). Phased LSTM: Accelerating neural network training for long or event-based sequences. In Butts, Weng, Jin, Yeh, Lesica, Alonso (b25) 2007; 449 Rao, Olshausen, Lewicki (b185) 2002 Le Roux, Bengio (b113) 2008; 20 Kullback, Leibler (b109) 1951; 22 Mozafari, Kheradpisheh, Masquelier, Nowzari-Dalini, Ganjtabesh (b157) 2018 Tavanaei, Maida (b226) 2018 Barra, Bernacchia, Santucci, Contucci (b6) 2012; 34 Hubel, Wiesel (b80) 1962; 160 1–9. Gütig, Sompolinsky (b64) 2006; 9 Abdel -Hamid, Deng, Yu (b1) 2013 Hochreiter, Schmidhuber (b74) 1997; 9 Krizhevsky, Sutskever, Hinton (b107) 2012 1–16. Pfister, Toyoizumi, Barber, Gerstner (b180) 2006; 18 Zylberberg, Murphy, DeWeese (b248) 2011; 7 . Hunsberger, E., & Eliasmith, C. (2015). Spiking deep networks with LIF neurons, arXiv preprint Stromatias, Neil, Pfeiffer, Galluppi, Furber, Liu (b213) 2015; 9 Felleman, Van Essen (b49) 1991; 1 Hunsberger, E., & Eliasmith, C. (2016). Training spiking deep networks for neuromorphic hardware, arXiv preprint Diehl, Neil, Binas, Cook, Liu, Pfeiffer (b40) 2015 Lamb, A., Goyal, A., Zhang, Y., Zhang, S., Courville, A., & Bengio, Y. (2016). Professor forcing: A new algorithm for training recurrent networks, arXiv preprint Pecevski, Maass (b176) 2016 Tang, Chehayeb, Srivastava, Nemenman, Sober (b218) 2014; 12 Eliasmith, Stewart, Choo, Bekolay, DeWolf, Tang (b44) 2012; 338 Escobar, Masson, Vieville, Kornprobst (b46) 2009; 82 Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014). Learning and transferring mid-level image representations using convolutional neural networks. In Neftci, Augustine, Paul, Detorakis (b160) 2017; 11 Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Tavanaei, A., & Maida, A. S. (2016). Bio-inspired spiking convolutional neural network using layer-wise sparse coding and STDP learning, arXiv preprint Seo, Brezzo, Liu, Parker, Esser, Montoye (b202) 2011 Seung (b204) 2003; 40 Bohte, La Poutré, Kok (b19) 2002; 13 Liu, P., Han, S., Meng, Z., & Tong, Y. (2014). Facial expression recognition via a boosted deep belief network. In (pp. 1805–1812). Tavanaei, Maida (b227) 2018; 90 Beyeler, Dutt, Krichmar (b15) 2013; 48 Kandel, Schwartz, Jessell, Siegelbaum, Hudspeth (b88) 2013 Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Dayan, Abbott (b36) 2001 Kasabov (b91) 2012 Lillicrap, Cownden, Tweed, Akerman (b124) 2016 Ghosh-Dastidar, Adeli (b57) 2009; 22 Kistler, Gerstner, van Hemmen (b102) 1997; 9 Pyle, Rosenbaum (b182) 2017; 118 Ponulak, Kasinski (b181) 2010; 22 Quang, Xie (b183) 2016; 44 (pp. 580–587). Shrestha, Ahmed, Wang, Widemann, Moody, Van Essen (b205) 2017 1–14. Pfeiffer, Pfeil (b178) 2018; 12 Indiveri, Corradi, Qiao (b84) 2015 Mainen, Sejnowski (b136) 1995; 268 Liu, Liu, Lin, Jin, Quan, Wen (b126) 2017 Marĉelja (b138) 1980; 70 Näger, Storck, Deco (b159) 2002; 44 Savin, Joshi, Triesch (b198) 2010; 6 Rueckauer, Hu, Lungu, Pfeiffer, Liu (b193) 2017; 11 Pfister, Gerstner (b179) 2006; 26 Masquelier, Thorpe (b144) 2010 Russakovsky, Deng, Su, Krause, Satheesh, Ma (b195) 2015; 115 Stromatias, Soto, Serrano -Gotarredona, Linares -Barranco (b214) 2017; 11 (pp. 2818–2826). Markram, Gerstner, Sjöström (b139) 2011; 3 Freiwald, Tsao (b52) 2010; 330 Cao, Chen, Khosla (b26) 2015; 113 Deng, Dong, Socher, Li, Li, Fei -Fei (b38) 2009 Maass (b133) 1997; 10 Merolla, Arthur, Akopyan, Imam, Manohar, Modha (b146) 2011 Bengio, Mesnard, Fischer, Zhang, Wu (b13) 2017 Zemel, Natarajan, Dayan, Huys (b244) 2004 Costa, Assael, Shillingford, de Freitas, Vogels (b33) 2017 Tavanaei, Masquelier, Maida (b229) 2016 Victor (b235) 2005; 15 Buesing, Bill, Nessler, Maass (b23) 2011; 7 Lee, Grosse, Ranganath, Ng (b121) 2011; 54 Thiele, Bichler, Dupret (b231) 2018; 12 Tubiana, Monasson (b232) 2017; 118 (pp. 3431–3440). Kheradpisheh, Ganjtabesh, Masquelier (b97) 2016; 205 Hopfield (b78) 1995; 376 Tavanaei, Maida (b225) 2017 He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Loiselle, Rouat, Pressnitzer, Thorpe (b128) 2005; Vol. 4 Bengio, Y., Lee, D. -H., Bornschein, J., Mesnard, T., & Lin, Z. (2015). Towards biologically plausible deep learning, arXiv preprint Hinton, Deng, Yu, Dahl, Mohamed, Jaitly (b72) 2012; 29 Mozer, Pashler, Homaei (b158) 2008; 32 Hodgkin, Huxley (b76) 1952; 117 Neil, Liu (b162) 2014; 22 Hopfield (b77) 1982; 79 Mohamed, Dahl, Hinton (b151) 2012; 20 Brader, Senn, Fusi (b21) 2007; 19 Kasinski, Ponulak (b96) 2006; 16 Diehl, Cook (b39) 2015; 9 Tavanaei, Masquelier, Maida (b230) 2018; 105 Földiak (b51) 1990; 64 Stone (b211) 2018 Lukoševičius, Jaeger (b130) 2009; 3 Burbank (b24) 2015; 11 Goodfellow, Bengio, Courville (b61) 2016 Song, Pan, Păun (b209) 2013; 219 (pp. 770–778). Morrison, Aertsen, Diesmann (b154) 2007; 19 Carrillo, Harkin, McDaid, Morgan, Pande, Cawley (b28) 2013; 24 Masquelier, Guyonneau, Thorpe (b140) 2008; 3 Tavanaei, Maida, Kaniymattam, Loganantharaj (b228) 2016 Wysoski, Benuskova, Kasabov (b241) 2008; 71 Lee, Delbruck, Pfeiffer (b119) 2016; 10 Sainath, Mohamed, Kingsbury, Ramabhadran (b196) 2013 Delorme, Gautrais, Van Rullen, Thorpe (b37) 1999; 26 Ghosh-Dastidar, Adeli (b58) 2009; 19 Panchev, Wermter (b173) 2004; 58 Barra, Genovese, Sollich, Tantari (b8) 2018; 97 Mozafari, M., Ganjtabesh, M., Nowzari -Dalini, A., Thorpe, S. J., & Masquelier, T. (2018a). Combining STDP and reward-modulated STDP in deep convolutional spiking neural networks for digit recognition, arXiv preprint Le Roux, Bengio (b114) 2010; 22 Wang, Belatreche, Maguire, McGinnity (b239) 2014; 144 Panda, Roy (b174) 2016 Liu, Pu, Poo (b127) 2005; 437 Salama, Hassanien, Fahmy (b197) 2010 Anwani, Rajendran (b4) 2015 Hinton, Osindero, Teh (b73) 2006; 18 Elman (b45) 1990; 14 Masquelier, Thorpe (b143) 2007; 3 Ghosh-Dastidar, Adeli (b56) 2007; 14 Lee, Pham, Largman, Ng (b122) 2009 Meftah, Lezoray, Benyettou (b145) 2010; 32 Kasabov (b92) 2014; 52 Herikstad, Baker, Lachaux, Gray, Yen (b69) 2011; 31 Ronneberger, Fischer, Brox (b191) 2015 Nessler, Pfeiffer, Buesing, Maass (b166) 2013; 9 99. Bishop (b16) 1995 Krizhevsky, A., & Hinton, G. (2010). Convolutional deep belief networks on CIFAR-10, Unpublished Manuscript 40. Hertz, Krogh, Palmer (b70) 1991 Hubel, Wiesel (b79) 1959; 148 Krizhevsky, Hinton (b105) 2009 Masquelier, Guyonneau, Thorpe (b141) 2009; 21 Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint Tavanaei, Maida (b223) 2017 Tavanaei, Maida (b224) 2017; 240 Mleczko, Kapuściński, Nowicki (b149) 2015 Diehl, P. U., Zarrella, G., Cassidy, A., Pedroni, B. U., & Neftci, E. (2016). Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware. In Masquelier, T., & Kheradpisheh, S. R. (2018). Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection, arXiv preprint Lukoševičius, Jaeger, Schrauwen (b131) 2012; 26 Maass (b134) 2015; 103 Sengupta, A., Ye, Y., Wang, R., Liu, C., & Roy, K. (2018). Going deeper in spiking networks: VGG and residual architectures, arXiv [Preprint]. Bair, Koch (b5) 1996; 8 Rueckauer, B., Lungu, I. -A., Hu, Y., & Pfeiffer, M. (2016). Theory and tools for the conversion of analog to spiking convolutional neural networks, arXiv preprint Rezende, Wierstra, Gerstner (b189) 2011 Hinton (b71) 2007; Vol. 656 O’Connor, P., & Welling, M. (2016). Deep spiking networks, arXiv preprint Akopyan, Sawada, Cassidy, Alvarez -Icaza, Arthur, Merolla (b3) 2015; 34 Kasabov (b93) 2018 Neil, Pfeiffer, Liu (b165) 2016 Gerstner, Kistler, Naud, Paninski (b55) 2014 Nessler, Pfeiffer, Maass (b167) 2009 Esser, Merolla, Arthur, Cassidy, Appuswamy, Andreopoulos (b48) 2016 Susskind, Hinton, Movellan, Anderson (b215) 2008 Mostafa (b155) 2017 Yu, Tang, Tan, Yu (b243) 2014; 138 Gupta, Long (b63) 2007 Olshausen (b170) 1996; 381 Hochreiter, Younger, Conwell (b75) 2001 Jolivet, Timothy, Gerstner (b87) 2003 Mohamed, Dahl, Hinton (b150) 2009; Vol. 1 Orchard, Jayawant, Cohen, Thakor (b172) 2015; 9 Jo, Hou, Eickholt, Cheng (b86) 2015; 5 Kasabov, Dhoble, Nuntalid, Indiveri (b94) 2013; 41 Grossberg (b62) 1987; 11 Kasabov, Feigin, Hou, Chen, Liang, Krishnamurthi (b95) 2014; 134 Serre (b203) 2014 Caporale, Dan (b27) 2008; 31 Hamel, Eck (b66) 2010; Vol. 10 Kröger, Kannampuzha, Neuschaefer -Rube (b108) 2009; 51 Doborjeh, Kasabov, Doborjeh, Sumich (b42) 2018; 8 Esser, Appuswamy, Merolla, Arthur, Modha (b47) 2015 Tavanaei, Maida (b220) 2015; 4 Bellec, G., Salaj, D., Subramoney, A., Legenstein, R., & Maass, W. (2018). Long short-term memory and learning-to-learn in networks of spiking neurons, arXiv preprint Kheradpisheh, Ghodrati, Ganjtabesh, Masquelier (b100) 2016; 6 Gerstner, Kistler (b54) 2002 LeCun, Bengio, Hinton (b115) 2015; 521 Florian (b50) 2012; 7 Song, Miller, Abbott (b208) 2000; 3 Mohemmed, Schliebs, Matsuda, Kasabov (b152) 2012; 22 (pp. 3889–3897). Doya (b43) 2007 King, Zylberberg, DeWeese (b101) 2013; 33 Maass (b132) 1996; 8 Barra, Genovese, Sollich, Tantari (b7) 2017; 96 Wade, McDaid, Santos, Sayers (b238) 2010; 21 Szegedy, Liu, Jia, Sermanet, Reed, Anguelov (b216) 2015 Carrillo, Harkin, McDaid, Pande, Cawley, McGinley (b29) 2012; 33 Reinagel, Reid (b188) 2000; 20 LeCun, Y., Cortes, C., & Burges, C. J. (1998b). The MNIST database, URL Querlioz, Bichler, Dollfus, Gamrat (b184) 2013; 12 Wu, Y., Deng, L., Li, G., Zhu, J., & Shi, L. (2017). Spatio-temporal backpropagation for training high-performance spiking neural networks, arXiv preprint Izhikevich (b85) 2003; 14 Rehn, Sommer (b187) 2007; 22 Mamoshina, Vieira, Putin, Zhavoronkov (b137) 2016; 13 Klampfl, Maass (b103) 2013; 33 Neftci, Das, Pedroni, Kreutz -Delgado, Cauwenberghs (b161) 2014; 8 Booij, tat Nguyen (b20) 2005; 95 Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv preprint LeCun, Bottou, Bengio, Haffner (b116) 1998; 86 Rawat, Wang (b186) 2017 Kheradpisheh, Maass (10.1016/j.neunet.2018.12.002_b132) 1996; 8 Schliebs (10.1016/j.neunet.2018.12.002_b199) 2011 Brea (10.1016/j.neunet.2018.12.002_b22) 2011 Susskind (10.1016/j.neunet.2018.12.002_b215) 2008 Tavanaei (10.1016/j.neunet.2018.12.002_b223) 2017 Le Roux (10.1016/j.neunet.2018.12.002_b113) 2008; 20 Mohamed (10.1016/j.neunet.2018.12.002_b150) 2009; Vol. 1 Mozer (10.1016/j.neunet.2018.12.002_b158) 2008; 32 Stromatias (10.1016/j.neunet.2018.12.002_b214) 2017; 11 Crick (10.1016/j.neunet.2018.12.002_b34) 1998; 391 Salama (10.1016/j.neunet.2018.12.002_b197) 2010 Rozenberg (10.1016/j.neunet.2018.12.002_b192) 2011 Vreeken (10.1016/j.neunet.2018.12.002_b237) 2003 Barra (10.1016/j.neunet.2018.12.002_b7) 2017; 96 Krizhevsky (10.1016/j.neunet.2018.12.002_b107) 2012 Liu (10.1016/j.neunet.2018.12.002_b127) 2005; 437 Seung (10.1016/j.neunet.2018.12.002_b204) 2003; 40 Bishop (10.1016/j.neunet.2018.12.002_b16) 1995 Lee (10.1016/j.neunet.2018.12.002_b119) 2016; 10 Rezende (10.1016/j.neunet.2018.12.002_b189) 2011 Eliasmith (10.1016/j.neunet.2018.12.002_b44) 2012; 338 10.1016/j.neunet.2018.12.002_b194 Gerstner (10.1016/j.neunet.2018.12.002_b54) 2002 Lee (10.1016/j.neunet.2018.12.002_b121) 2011; 54 Pfister (10.1016/j.neunet.2018.12.002_b179) 2006; 26 Hopfield (10.1016/j.neunet.2018.12.002_b77) 1982; 79 Masquelier (10.1016/j.neunet.2018.12.002_b140) 2008; 3 Doborjeh (10.1016/j.neunet.2018.12.002_b42) 2018; 8 Pfeiffer (10.1016/j.neunet.2018.12.002_b178) 2018; 12 Bohte (10.1016/j.neunet.2018.12.002_b19) 2002; 13 Meftah (10.1016/j.neunet.2018.12.002_b145) 2010; 32 Tavanaei (10.1016/j.neunet.2018.12.002_b224) 2017; 240 Zylberberg (10.1016/j.neunet.2018.12.002_b248) 2011; 7 Quang (10.1016/j.neunet.2018.12.002_b183) 2016; 44 Ghosh-Dastidar (10.1016/j.neunet.2018.12.002_b56) 2007; 14 Liu (10.1016/j.neunet.2018.12.002_b126) 2017 Dayan (10.1016/j.neunet.2018.12.002_b36) 2001 Deng (10.1016/j.neunet.2018.12.002_b38) 2009 Venna (10.1016/j.neunet.2018.12.002_b234) 2017 Lagorce (10.1016/j.neunet.2018.12.002_b111) 2017; 38 Abdel -Hamid (10.1016/j.neunet.2018.12.002_b1) 2013 Mohemmed (10.1016/j.neunet.2018.12.002_b153) 2013; 107 Hubel (10.1016/j.neunet.2018.12.002_b80) 1962; 160 10.1016/j.neunet.2018.12.002_b81 O’Connor (10.1016/j.neunet.2018.12.002_b168) 2013; 7 10.1016/j.neunet.2018.12.002_b82 10.1016/j.neunet.2018.12.002_b83 Tubiana (10.1016/j.neunet.2018.12.002_b232) 2017; 118 Masquelier (10.1016/j.neunet.2018.12.002_b143) 2007; 3 Pecevski (10.1016/j.neunet.2018.12.002_b176) 2016 Seo (10.1016/j.neunet.2018.12.002_b202) 2011 Escobar (10.1016/j.neunet.2018.12.002_b46) 2009; 82 Bair (10.1016/j.neunet.2018.12.002_b5) 1996; 8 Kullback (10.1016/j.neunet.2018.12.002_b109) 1951; 22 Merolla (10.1016/j.neunet.2018.12.002_b146) 2011 Garbin (10.1016/j.neunet.2018.12.002_b53) 2014 Guyonneau (10.1016/j.neunet.2018.12.002_b65) 2005; 17 Perez-Carrasko (10.1016/j.neunet.2018.12.002_b177) 2013; 35 Körding (10.1016/j.neunet.2018.12.002_b104) 2004; 427 Song (10.1016/j.neunet.2018.12.002_b208) 2000; 3 Srivastava (10.1016/j.neunet.2018.12.002_b210) 2017 Bohte (10.1016/j.neunet.2018.12.002_b18) 2002; 48 Bohte (10.1016/j.neunet.2018.12.002_b17) 2004; 3 Russakovsky (10.1016/j.neunet.2018.12.002_b195) 2015; 115 Beyeler (10.1016/j.neunet.2018.12.002_b15) 2013; 48 Wang (10.1016/j.neunet.2018.12.002_b239) 2014; 144 Maass (10.1016/j.neunet.2018.12.002_b133) 1997; 10 Wade (10.1016/j.neunet.2018.12.002_b238) 2010; 21 Olshausen (10.1016/j.neunet.2018.12.002_b170) 1996; 381 Rao (10.1016/j.neunet.2018.12.002_b185) 2002 Mostafa (10.1016/j.neunet.2018.12.002_b155) 2017 Neftci (10.1016/j.neunet.2018.12.002_b161) 2014; 8 Maass (10.1016/j.neunet.2018.12.002_b135) 2002; 14 Ghosh-Dastidar (10.1016/j.neunet.2018.12.002_b58) 2009; 19 Lee (10.1016/j.neunet.2018.12.002_b122) 2009 Hochreiter (10.1016/j.neunet.2018.12.002_b74) 1997; 9 Masquelier (10.1016/j.neunet.2018.12.002_b141) 2009; 21 Min (10.1016/j.neunet.2018.12.002_b148) 2017; 18 Serre (10.1016/j.neunet.2018.12.002_b203) 2014 Ghosh-Dastidar (10.1016/j.neunet.2018.12.002_b57) 2009; 22 Caporale (10.1016/j.neunet.2018.12.002_b27) 2008; 31 Lillicrap (10.1016/j.neunet.2018.12.002_b124) 2016 Ronneberger (10.1016/j.neunet.2018.12.002_b191) 2015 Mainen (10.1016/j.neunet.2018.12.002_b136) 1995; 268 Schmidhuber (10.1016/j.neunet.2018.12.002_b200) 2015; 61 Kasabov (10.1016/j.neunet.2018.12.002_b94) 2013; 41 Näger (10.1016/j.neunet.2018.12.002_b159) 2002; 44 Neftci (10.1016/j.neunet.2018.12.002_b160) 2017; 11 Nessler (10.1016/j.neunet.2018.12.002_b167) 2009 Marĉelja (10.1016/j.neunet.2018.12.002_b138) 1980; 70 Carrillo (10.1016/j.neunet.2018.12.002_b29) 2012; 33 Song (10.1016/j.neunet.2018.12.002_b209) 2013; 219 Zeng (10.1016/j.neunet.2018.12.002_b245) 2016; 32 Hertz (10.1016/j.neunet.2018.12.002_b70) 1991 Tavanaei (10.1016/j.neunet.2018.12.002_b228) 2016 Bell (10.1016/j.neunet.2018.12.002_b9) 1997; 37 10.1016/j.neunet.2018.12.002_b206 Victor (10.1016/j.neunet.2018.12.002_b236) 1997; 8 10.1016/j.neunet.2018.12.002_b201 Tavanaei (10.1016/j.neunet.2018.12.002_b230) 2018; 105 Elman (10.1016/j.neunet.2018.12.002_b45) 1990; 14 Burbank (10.1016/j.neunet.2018.12.002_b24) 2015; 11 Tavanaei (10.1016/j.neunet.2018.12.002_b229) 2016 LeCun (10.1016/j.neunet.2018.12.002_b115) 2015; 521 Markram (10.1016/j.neunet.2018.12.002_b139) 2011; 3 Hinton (10.1016/j.neunet.2018.12.002_b71) 2007; Vol. 656 Ponulak (10.1016/j.neunet.2018.12.002_b181) 2010; 22 Pyle (10.1016/j.neunet.2018.12.002_b182) 2017; 118 Carrillo (10.1016/j.neunet.2018.12.002_b28) 2013; 24 Gerstner (10.1016/j.neunet.2018.12.002_b55) 2014 Krizhevsky (10.1016/j.neunet.2018.12.002_b105) 2009 10.1016/j.neunet.2018.12.002_b217 Gupta (10.1016/j.neunet.2018.12.002_b63) 2007 Lee (10.1016/j.neunet.2018.12.002_b120) 2008 10.1016/j.neunet.2018.12.002_b12 10.1016/j.neunet.2018.12.002_b10 Orchard (10.1016/j.neunet.2018.12.002_b172) 2015; 9 Morrison (10.1016/j.neunet.2018.12.002_b154) 2007; 19 Zenke (10.1016/j.neunet.2018.12.002_b246) 2017; 30 Herikstad (10.1016/j.neunet.2018.12.002_b69) 2011; 31 Kheradpisheh (10.1016/j.neunet.2018.12.002_b99) 2016; 10 Reinagel (10.1016/j.neunet.2018.12.002_b188) 2000; 20 Tavanaei (10.1016/j.neunet.2018.12.002_b226) 2018 10.1016/j.neunet.2018.12.002_b106 10.1016/j.neunet.2018.12.002_b222 Wysoski (10.1016/j.neunet.2018.12.002_b241) 2008; 71 Kasabov (10.1016/j.neunet.2018.12.002_b92) 2014; 52 Butts (10.1016/j.neunet.2018.12.002_b25) 2007; 449 Tavanaei (10.1016/j.neunet.2018.12.002_b219) 2018 Gütig (10.1016/j.neunet.2018.12.002_b64) 2006; 9 LeCun (10.1016/j.neunet.2018.12.002_b116) 1998; 86 Shrestha (10.1016/j.neunet.2018.12.002_b205) 2017 Esser (10.1016/j.neunet.2018.12.002_b47) 2015 Izhikevich (10.1016/j.neunet.2018.12.002_b85) 2003; 14 Stromatias (10.1016/j.neunet.2018.12.002_b213) 2015; 9 Querlioz (10.1016/j.neunet.2018.12.002_b184) 2013; 12 Masquelier (10.1016/j.neunet.2018.12.002_b144) 2010 Kang (10.1016/j.neunet.2018.12.002_b89) 2013 Doya (10.1016/j.neunet.2018.12.002_b43) 2007 Mohemmed (10.1016/j.neunet.2018.12.002_b152) 2012; 22 Dan (10.1016/j.neunet.2018.12.002_b35) 2006; 86 Goodfellow (10.1016/j.neunet.2018.12.002_b61) 2016 Kheradpisheh (10.1016/j.neunet.2018.12.002_b98) 2018; 99 Rieke (10.1016/j.neunet.2018.12.002_b190) 1999 10.1016/j.neunet.2018.12.002_b117 10.1016/j.neunet.2018.12.002_b118 10.1016/j.neunet.2018.12.002_b112 Mozafari (10.1016/j.neunet.2018.12.002_b157) 2018 Victor (10.1016/j.neunet.2018.12.002_b235) 2005; 15 Hinton (10.1016/j.neunet.2018.12.002_b73) 2006; 18 10.1016/j.neunet.2018.12.002_b240 Rehn (10.1016/j.neunet.2018.12.002_b187) 2007; 22 Nessler (10.1016/j.neunet.2018.12.002_b166) 2013; 9 Barra (10.1016/j.neunet.2018.12.002_b8) 2018; 97 Florian (10.1016/j.neunet.2018.12.002_b50) 2012; 7 Felleman (10.1016/j.neunet.2018.12.002_b49) 1991; 1 Földiak (10.1016/j.neunet.2018.12.002_b51) 1990; 64 Hopfield (10.1016/j.neunet.2018.12.002_b78) 1995; 376 Maass (10.1016/j.neunet.2018.12.002_b134) 2015; 103 Klampfl (10.1016/j.neunet.2018.12.002_b103) 2013; 33 Tavanaei (10.1016/j.neunet.2018.12.002_b227) 2018; 90 Hochreiter (10.1016/j.neunet.2018.12.002_b75) 2001 10.1016/j.neunet.2018.12.002_b129 10.1016/j.neunet.2018.12.002_b125 Pfister (10.1016/j.neunet.2018.12.002_b180) 2006; 18 Savin (10.1016/j.neunet.2018.12.002_b198) 2010; 6 Anwani (10.1016/j.neunet.2018.12.002_b4) 2015 Lukoševičius (10.1016/j.neunet.2018.12.002_b130) 2009; 3 Costa (10.1016/j.neunet.2018.12.002_b33) 2017 Kasinski (10.1016/j.neunet.2018.12.002_b96) 2006; 16 Le Roux (10.1016/j.neunet.2018.12.002_b114) 2010; 22 Bengio (10.1016/j.neunet.2018.12.002_b11) 2009; 2 Tavanaei (10.1016/j.neunet.2018.12.002_b225) 2017 Akopyan (10.1016/j.neunet.2018.12.002_b3) 2015; 34 Chavez-Noriega (10.1016/j.neunet.2018.12.002_b30) 1990; 79 Delorme (10.1016/j.neunet.2018.12.002_b37) 1999; 26 Freiwald (10.1016/j.neunet.2018.12.002_b52) 2010; 330 VanRullen (10.1016/j.neunet.2018.12.002_b233) 2017; 8 Esser (10.1016/j.neunet.2018.12.002_b48) 2016 10.1016/j.neunet.2018.12.002_b142 Rueckauer (10.1016/j.neunet.2018.12.002_b193) 2017; 11 Stromatias (10.1016/j.neunet.2018.12.002_b212) 2015 10.1016/j.neunet.2018.12.002_b59 Kandel (10.1016/j.neunet.2018.12.002_b88) 2013 Panda (10.1016/j.neunet.2018.12.002_b174) 2016 Tang (10.1016/j.neunet.2018.12.002_b218) 2014; 12 Grossberg (10.1016/j.neunet.2018.12.002_b62) 1987; 11 Jolivet (10.1016/j.neunet.2018.12.002_b87) 2003 Kröger (10.1016/j.neunet.2018.12.002_b108) 2009; 51 Brader (10.1016/j.neunet.2018.12.002_b21) 2007; 19 Hodgkin (10.1016/j.neunet.2018.12.002_b76) 1952; 117 Bengio (10.1016/j.neunet.2018.12.002_b13) 2017 Diehl (10.1016/j.neunet.2018.12.002_b39) 2015; 9 Kheradpisheh (10.1016/j.neunet.2018.12.002_b100) 2016; 6 Kistler (10.1016/j.neunet.2018.12.002_b102) 1997; 9 Mohamed (10.1016/j.neunet.2018.12.002_b151) 2012; 20 Bengio (10.1016/j.neunet.2018.12.002_b14) 1994; 5 Lukoševičius (10.1016/j.neunet.2018.12.002_b131) 2012; 26 Sainath (10.1016/j.neunet.2018.12.002_b196) 2013 Kasabov (10.1016/j.neunet.2018.12.002_b93) 2018 Kuremoto (10.1016/j.neunet.2018.12.002_b110) 2014; 137 Hassabis (10.1016/j.neunet.2018.12.002_b67) 2017; 95 10.1016/j.neunet.2018.12.002_b68 Panchev (10.1016/j.neunet.2018.12.002_b173) 2004; 58 Kasabov (10.1016/j.neunet.2018.12.002_b91) 2012 Mleczko (10.1016/j.neunet |
| References_xml | – volume: 31 start-page: 25 year: 2008 end-page: 46 ident: b27 article-title: Spike timing-dependent plasticity: A Hebbian learning rule publication-title: Annual Review of Neuroscience – reference: Neil, D., Pfeiffer, M., & Liu, S. (2016a). Phased LSTM: Accelerating neural network training for long or event-based sequences. In – volume: 5 year: 2015 ident: b86 article-title: Improving protein fold recognition by deep learning networks publication-title: Scientific Reports – start-page: 846 year: 2003 end-page: 853 ident: b87 article-title: The spike response model: A framework to predict neuronal spike trains publication-title: Artificial neural networks and neural information processing—ICANN/ICONIP 2003 – volume: 12 start-page: 1 year: 2018 end-page: 13 ident: b231 article-title: Event-based, timescale invariant unsupervised online learning with STDP publication-title: Frontiers in Computational Neuroscience – start-page: 1357 year: 2009 end-page: 1365 ident: b167 article-title: STDP enables spiking neurons to detect hidden causes of their inputs publication-title: Advances in neural information processing systems – start-page: 1 year: 2015 end-page: 8 ident: b4 article-title: Normad-normalized approximate descent based supervised learning rule for spiking neurons publication-title: 2015 international joint conference on neural networks – start-page: 1 year: 2015 end-page: 8 ident: b212 article-title: Scalable energy-efficient, low-latency implementations of trained spiking deep belief networks on spinnaker publication-title: Neural networks, 2015 international joint conference on – start-page: 3366 year: 2013 end-page: 3370 ident: b1 article-title: Exploring convolutional neural network structures and optimization techniques for speech recognition publication-title: Interspeech – reference: Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014). Learning and transferring mid-level image representations using convolutional neural networks. In – reference: Tavanaei, A., & Maida, A. S. (2016). Bio-inspired spiking convolutional neural network using layer-wise sparse coding and STDP learning, arXiv preprint – volume: 21 start-page: 1817 year: 2010 end-page: 1830 ident: b238 article-title: SWAT: A spiking neural network training algorithm for classification problems publication-title: IEEE Transactions on Neural Networks – start-page: 87 year: 2001 end-page: 94 ident: b75 article-title: Learning to learn using gradient descent publication-title: Intl conf on artificial neural networks – start-page: 8012 year: 2013 end-page: 8016 ident: b89 article-title: Multi-distribution deep belief network for speech synthesis publication-title: Acoustics, speech and signal processing, 2013 IEEE international conference on – volume: 3 year: 2007 ident: b143 article-title: Unsupervised learning of visual features through spike timing dependent plasticity publication-title: PLoS Computational Biology – volume: 26 start-page: 1963 year: 2015 end-page: 1978 ident: b247 article-title: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 376 start-page: 33 year: 1995 end-page: 36 ident: b78 article-title: Pattern recognition computation using action potential timing for stimulus representation publication-title: Nature – volume: 52 start-page: 62 year: 2014 end-page: 76 ident: b92 article-title: NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data publication-title: Neural Networks – volume: 3 start-page: 195 year: 2004 end-page: 206 ident: b17 article-title: The evidence for neural information processing with precise spike-times: A survey publication-title: Natural Computing – volume: 26 start-page: 9673 year: 2006 end-page: 9682 ident: b179 article-title: Triplets of spikes in a model of spike timing-dependent plasticity publication-title: Journal of Neuroscience – volume: 148 start-page: 574 year: 1959 end-page: 591 ident: b79 article-title: Receptive fields of single neurones in the cat’s striate cortex publication-title: The Journal of Physiology – start-page: 631 year: 2017 end-page: 637 ident: b205 article-title: A spike-based long short-term memory on a neurosynaptic processor publication-title: Computer-aided design, 2017 IEEE/ACM international conference on – start-page: 873 year: 2008 end-page: 880 ident: b120 article-title: Sparse deep belief net model for visual area V2 publication-title: Advances in neural information processing systems – start-page: 1 year: 2011 end-page: 4 ident: b202 article-title: A 45nm cmos neuromorphic chip with a scalable architecture for learning in networks of spiking neurons publication-title: Custom integrated circuits conference, 2011 IEEE – volume: 70 start-page: 1297 year: 1980 end-page: 1300 ident: b138 article-title: Mathematical description of the responses of simple cortical cells publication-title: Journal of the Optical Society of America – volume: 79 start-page: 2554 year: 1982 end-page: 2558 ident: b77 article-title: Neural networks and physical systems with emergent collective computational abilities publication-title: Proceedings of the National Academy of Sciences – volume: 22 start-page: 2621 year: 2014 end-page: 2628 ident: b162 article-title: Minitaur, an event-driven FPGA-based spiking network accelerator publication-title: IEEE Transactions on Very Large Scale Integration (VLSI) Systems – reference: Cireşan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification, arXiv preprint – volume: 22 start-page: 79 year: 1951 end-page: 86 ident: b109 article-title: On information and sufficiency publication-title: The Annals of Mathematical Statistics – start-page: 1 year: 2015 end-page: 8 ident: b40 article-title: Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing publication-title: Neural networks, 2015 international joint conference on – volume: 118 year: 2017 ident: b182 article-title: Spatiotemporal dynamics and reliable computations in recurrent spiking neural networks publication-title: Physical Review Letters – volume: 9 start-page: 1015 year: 1997 end-page: 1045 ident: b102 article-title: Reduction of the Hodgkin-Huxley equations to a single-variable threshold model publication-title: Neural Computation – volume: 44 start-page: 937 year: 2002 end-page: 942 ident: b159 article-title: Speech recognition with spiking neurons and dynamic synapses: A model motivated by the human auditory pathway publication-title: Neurocomputing – volume: 14 start-page: 179 year: 1990 end-page: 211 ident: b45 article-title: Finding structure in time publication-title: Cognitive Science – reference: Masquelier, T., & Kheradpisheh, S. R. (2018). Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection, arXiv preprint – start-page: 1422 year: 2011 end-page: 1430 ident: b22 article-title: Sequence learning with hidden units in spiking neural networks publication-title: Advances in neural information processing systems – volume: 16 start-page: 101 year: 2006 end-page: 113 ident: b96 article-title: Comparison of supervised learning platforms for spike time coding in spiking neural networks publication-title: International Journal of Applied Mathematics and Computer Science – start-page: 450 year: 2017 end-page: 457 ident: b126 article-title: MT-spike: A multilayer time-based spiking neuromorphic architecture with temporal error backpropagation publication-title: Proceedings of the 36th international conference on computer-aided design – year: 1995 ident: b16 article-title: Neural networks for pattern recognition – volume: 8 start-page: 1185 year: 1996 end-page: 1202 ident: b5 article-title: Temporal precision of spike trains in extrastriate cortex of the behaving macaque monkey publication-title: Neural Computation – volume: 17 start-page: 859 year: 2005 end-page: 879 ident: b65 article-title: Neurons tune to the earliest spikes through STDP publication-title: Neural Computation – volume: 26 start-page: 989 year: 1999 end-page: 996 ident: b37 article-title: SpikeNET: A simulator for modeling large networks of integrate and fire neurons publication-title: Neurocomputing – volume: 345 start-page: 668 year: 2014 end-page: 673 ident: b147 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science – year: 1999 ident: b190 article-title: Spikes: Exploring the neural code – start-page: 473 year: 2010 end-page: 477 ident: b197 article-title: Deep belief network for clustering and classification of a continuous data publication-title: Signal processing and information technology, 2010 IEEE international symposium on – volume: 14 start-page: 2531 year: 2002 end-page: 2560 ident: b135 article-title: Real-time computing without stable states: A new framework for neural computation based on perturbations publication-title: Neural Computation – volume: 79 start-page: 633 year: 1990 end-page: 641 ident: b30 article-title: A decrease in firing threshold observed after induction of the EPSP-spike (ES) component of long-term potentiation in rat hippocampal slices publication-title: Experimental Brain Research – volume: Vol. 4 start-page: 2076 year: 2005 end-page: 2080 ident: b128 article-title: Exploration of rank order coding with spiking neural networks for speech recognition publication-title: Neural networks, 2005. IJCNN’05. Proceedings. 2005 IEEE international joint conference on – volume: 12 year: 2014 ident: b218 article-title: Millisecond-scale motor encoding in a cortical vocal area publication-title: PLoS Biology – start-page: 1 year: 2014 end-page: 4 ident: b53 article-title: Variability-tolerant convolutional neural network for pattern recognition applications based on oxram synapses publication-title: Electron devices meeting, 2014 IEEE international – year: 2013 ident: b88 article-title: Principles of neural science – volume: 107 start-page: 3 year: 2013 end-page: 10 ident: b153 article-title: Training spiking neural networks to associate spatio-temporal input-output spike patterns publication-title: Neurocomputing – reference: Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In – reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In – volume: 22 start-page: 2192 year: 2010 end-page: 2207 ident: b114 article-title: Deep belief networks are compact universal approximators publication-title: Neural Computation – volume: 9 start-page: 1 year: 2015 end-page: 9 ident: b39 article-title: Unsupervised learning of digit recognition using spike-timing-dependent plasticity publication-title: Frontiers in Computational Neuroscience – volume: 427 start-page: 244 year: 2004 end-page: 247 ident: b104 article-title: Bayesian integration in sensorimotor learning publication-title: Nature – reference: Diehl, P. U., Zarrella, G., Cassidy, A., Pedroni, B. U., & Neftci, E. (2016). Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware. In – volume: 38 start-page: 1346 year: 2017 end-page: 1359 ident: b111 article-title: HOTS: A hierarchy of event-based time-surfaces for pattern recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 34 start-page: 1 year: 2012 end-page: 9 ident: b6 article-title: On the equivalence of Hopfield networks and Boltzmann machines publication-title: Neural Networks – year: 2011 ident: b192 article-title: Handbook of natural computing – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b74 article-title: Long short-term memory publication-title: Neural Computation – volume: 15 start-page: 585 year: 2005 end-page: 592 ident: b235 article-title: Spike train metrics publication-title: Current Opinion in Neurobiology – volume: 11 start-page: 324 year: 2017 ident: b160 article-title: Event-driven random back-propagation: Enabling neuromorphic deep learning machines publication-title: Frontiers in Neuroscience – start-page: 160 year: 2011 end-page: 168 ident: b199 article-title: Reservoir-based evolving spiking neural network for spatio-temporal pattern recognition publication-title: Neural information processing – start-page: 1 year: 2015 end-page: 6 ident: b221 article-title: Studying the interaction of a hidden Markov model with a Bayesian spiking neural network publication-title: Machine learning for signal processing, 2015 IEEE 25th international workshop on – start-page: 1609 year: 2004 end-page: 1616 ident: b244 article-title: Probabilistic computation in spiking populations publication-title: Advances in neural information processing systems – reference: (pp. 2818–2826). – start-page: 1 year: 2011 end-page: 4 ident: b146 article-title: A digital neurosynaptic core using embedded crossbar memory with 45pj per spike in 45nm publication-title: Custom integrated circuits conference, 2011 IEEE – start-page: 293 year: 2016 end-page: 298 ident: b165 article-title: Learning to be efficient: Algorithms for training low-latency, low-compute deep spiking neural networks publication-title: Proceedings of the 31st annual ACM symposium on applied computing – volume: 29 start-page: 82 year: 2012 end-page: 97 ident: b72 article-title: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups publication-title: IEEE Signal Processing Magazine – start-page: 2352 year: 2017 end-page: 2449 ident: b186 article-title: Deep convolutional neural networks for image classification: A comprehensive review publication-title: Neural Computation – start-page: 8614 year: 2013 end-page: 8618 ident: b196 article-title: Deep convolutional neural networks for LVCSR publication-title: Acoustics, speech and signal processing, 2013 IEEE international conference on – start-page: 1 year: 2016 end-page: 8 ident: b229 article-title: Acquisition of visual features through probabilistic spike timing dependent plasticity publication-title: Neural Networks, The 2016 international joint conference on – volume: 24 start-page: 2451 year: 2013 end-page: 2461 ident: b28 article-title: Scalable hierarchical network-on-chip architecture for spiking neural network hardware implementations publication-title: IEEE Transactions on Parallel and Distributed Systems – start-page: 1 year: 2018 end-page: 24 ident: b157 article-title: First-spike based visual categorization using reward-modulated STDP publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 31 start-page: 15844 year: 2011 end-page: 15860 ident: b69 article-title: Natural movies evoke spike trains with low spike time variability in cat primary visual cortex publication-title: Journal of Neuroscience – volume: 51 start-page: 793 year: 2009 end-page: 809 ident: b108 article-title: Towards a neurocomputational model of speech production and perception publication-title: Speech Communication – volume: 86 start-page: 1033 year: 2006 end-page: 1048 ident: b35 article-title: Spike timing-dependent plasticity: From synapse to perception publication-title: Physiological Reviews – volume: 11 start-page: 350 year: 2017 ident: b214 article-title: An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data publication-title: Frontiers in Neuroscience – volume: 3 start-page: 1 year: 2011 end-page: 24 ident: b139 article-title: A history of spike-timing-dependent plasticity publication-title: Frontiers in Synaptic Neuroscience – volume: 8 start-page: 1 year: 2014 end-page: 14 ident: b161 article-title: Event-driven contrastive divergence for spiking neuromorphic systems publication-title: Frontiers in Neuroscience – volume: 240 start-page: 191 year: 2017 end-page: 199 ident: b224 article-title: A spiking network that learns to extract spike signatures from speech signals publication-title: Neurocomputing – start-page: 81 year: 2017 end-page: 88 ident: b225 article-title: Multi-layer unsupervised learning in a spiking convolutional neural network publication-title: Neural Networks, 2017 international joint conference on – volume: Vol. 656 year: 2007 ident: b71 article-title: How to do backpropagation in a brain publication-title: Invited talk at the NIPS’2007 deep learning workshop – year: 2018 ident: b93 article-title: Time-space, spiking neural networks and brain-inspired artificial intelligence – reference: Mozafari, M., Ganjtabesh, M., Nowzari -Dalini, A., Thorpe, S. J., & Masquelier, T. (2018a). Combining STDP and reward-modulated STDP in deep convolutional spiking neural networks for digit recognition, arXiv preprint – start-page: 145 year: 2016 end-page: 149 ident: b228 article-title: Towards recognition of protein function based on its structure using deep convolutional networks publication-title: Bioinformatics and biomedicine, 2016 IEEE international conference on – volume: 33 start-page: 42 year: 2012 end-page: 57 ident: b29 article-title: Advancing interconnect density for spiking neural network hardware implementations using traffic-aware adaptive network-on-chip routers publication-title: Neural Networks – reference: Huh, D., & Sejnowski, T. J. (2017). Gradient descent for spiking neural networks, arXiv preprint – reference: Rueckauer, B., Lungu, I. -A., Hu, Y., & Pfeiffer, M. (2016). Theory and tools for the conversion of analog to spiking convolutional neural networks, arXiv preprint – volume: 5 start-page: 157 year: 1994 end-page: 166 ident: b14 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Transactions on Neural Networks – volume: 391 start-page: 245 year: 1998 end-page: 250 ident: b34 article-title: Constrains on cortical and thalamic projections: The no-strong-loops hypothesis publication-title: Nature – volume: 96 year: 2017 ident: b7 article-title: Phase transitions in restricted Boltzmann machines with generic priors publication-title: Physical Review E – volume: 40 start-page: 1063 year: 2003 end-page: 1073 ident: b204 article-title: Learning in spiking neural networks by reinforcement of stochastic synaptic transmission publication-title: Neuron – volume: 134 start-page: 269 year: 2014 end-page: 279 ident: b95 article-title: Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke publication-title: Neurocomputing – reference: LeCun, Y., Cortes, C., & Burges, C. J. (1998b). The MNIST database, URL – volume: 71 start-page: 2563 year: 2008 end-page: 2575 ident: b241 article-title: Fast and adaptive network of spiking neurons for multi-view visual pattern recognition publication-title: Neurocomputing – volume: 12 start-page: 1 year: 2018 end-page: 18 ident: b178 article-title: Deep learning with spiking neurons: Opportunities and challenges publication-title: Frontiers in Neuroscience – volume: 6 year: 2010 ident: b198 article-title: Independent component analysis in spiking neurons publication-title: PLoS Computational Biology – volume: 64 start-page: 165 year: 1990 end-page: 170 ident: b51 article-title: Forming sparse representations by local anti-hebbian learning publication-title: Biological Cybernetics – reference: . – volume: 22 start-page: 135 year: 2007 end-page: 146 ident: b187 article-title: A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields publication-title: Journal of Computational Neuroscience – volume: 48 start-page: 109 year: 2013 end-page: 124 ident: b15 article-title: Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule publication-title: Neural Networks – reference: (pp. 3431–3440). – volume: 330 start-page: 845 year: 2010 end-page: 851 ident: b52 article-title: Functional compartmentalization and viewpoint generalization within the macaque face-processing system publication-title: Science – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: b116 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE – volume: 54 start-page: 95 year: 2011 end-page: 103 ident: b121 article-title: Unsupervised learning of hierarchical representations with convolutional deep belief networks publication-title: Communications of the ACM – volume: Vol. 1 start-page: 39 year: 2009 ident: b150 article-title: Deep belief networks for phone recognition publication-title: NIPS workshop on deep learning for speech recognition and related applications – start-page: 272 year: 2017 end-page: 283 ident: b33 article-title: Cortical microcircuits as gated-recurrent neural networks publication-title: Advances in neural information processing systems – volume: 160 start-page: 106 year: 1962 end-page: 154 ident: b80 article-title: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex publication-title: The Journal of Physiology – volume: 9 year: 2013 ident: b166 article-title: Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity publication-title: PLoS Computational Biology – volume: 82 start-page: 284 year: 2009 end-page: 301 ident: b46 article-title: Action recognition using a bio-inspired feedforward spiking network publication-title: International Journal of Computer Vision – reference: , 1–10. – volume: 11 year: 1987 ident: b62 article-title: Competitive learning: From interactive activation to adaptive resonance publication-title: Cognitive Science – start-page: 248 year: 2009 end-page: 255 ident: b38 article-title: Imagenet: A large-scale hierarchical image database publication-title: Computer vision and pattern recognition, 2009. CVPR 2009. IEEE conference on – start-page: 1 year: 2018 end-page: 12 ident: b226 article-title: BP-STDP: Approximating Backpropagation using spike timing dependent plasticity publication-title: Neurocomputing – volume: Vol. 10 start-page: 339 year: 2010 end-page: 344 ident: b66 article-title: Learning features from music audio with deep belief networks publication-title: ISMIR – reference: LeCun, Y., et al. (2015b). LeNet-5, convolutional neural networks, URL: – year: 2015 ident: b84 article-title: Neuromorphic architectures for spiking deep neural networks publication-title: Electron devices meeting, 2015 IEEE international – reference: Sengupta, A., Ye, Y., Wang, R., Liu, C., & Roy, K. (2018). Going deeper in spiking networks: VGG and residual architectures, arXiv [Preprint]. – start-page: 53 year: 2007 end-page: 58 ident: b63 article-title: Character recognition using spiking neural networks publication-title: Neural networks, 2007. IJCNN 2007. International joint conference on – reference: Wu, Y., Deng, L., Li, G., Zhu, J., & Shi, L. (2017). Spatio-temporal backpropagation for training high-performance spiking neural networks, arXiv preprint – volume: 8 start-page: 127 year: 1997 end-page: 164 ident: b236 article-title: Metric-space analysis of spike trains: Theory, algorithms and application publication-title: Network. Computation in Neural Systems – volume: 137 start-page: 47 year: 2014 end-page: 56 ident: b110 article-title: Time series forecasting using a deep belief network with restricted Boltzmann machines publication-title: Neurocomputing – volume: 13 start-page: 1445 year: 2016 end-page: 1454 ident: b137 article-title: Applications of deep learning in biomedicine publication-title: Molecular Pharmaceutics – year: 2017 ident: b210 article-title: Motor control by precisely timed spike patterns publication-title: Proceedings of the National Academy of Sciences – volume: 13 start-page: 426 year: 2002 end-page: 435 ident: b19 article-title: Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks publication-title: IEEE Transactions on Neural Networks – reference: Hunsberger, E., & Eliasmith, C. (2015). Spiking deep networks with LIF neurons, arXiv preprint – reference: Liu, P., Han, S., Meng, Z., & Tong, Y. (2014). Facial expression recognition via a boosted deep belief network. In – year: 2002 ident: b54 article-title: Spiking neuron models: Single neurons, populations, plasticity – volume: 449 start-page: 92 year: 2007 end-page: 95 ident: b25 article-title: Temporal precision in the neural code and the timescales of natural vision publication-title: Nature – volume: 7 start-page: 1 year: 2013 end-page: 13 ident: b168 article-title: Real-time classification and sensor fusion with a spiking deep belief network publication-title: Frontiers in Neuroscience – volume: 118 year: 2017 ident: b232 article-title: Emergence of compositional representations in restricted Boltzmann machines publication-title: Physical Review Letters – volume: 8 start-page: 8912 year: 2018 ident: b42 article-title: Modelling peri-perceptual brain processes in a deep learning spiking neural network architecture publication-title: Scientific Reports – volume: 44 year: 2016 ident: b183 article-title: DanQ: A hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences publication-title: Nucleic Acids Research – reference: (pp. 1805–1812). – volume: 319 start-page: 1108 year: 2008 end-page: 1111 ident: b60 article-title: Rapid neural coding in the retina with relative spike latencies publication-title: Science – start-page: 1 year: 2009 end-page: 60 ident: b105 article-title: Learning multiple layers of features from tiny images – reference: Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In – volume: 18 start-page: 851 year: 2017 end-page: 869 ident: b148 article-title: Deep learning in bioinformatics publication-title: Briefings in Bioinformatics – start-page: 1 year: 2018 end-page: 8 ident: b219 article-title: Training spiking convnets by STDP and Gradient Descent publication-title: Neural networks, The 2018 international joint conference on – volume: 30 start-page: 1514 year: 2017 end-page: 1541 ident: b246 article-title: SuperSpike: Supervised learning in multi-layer spiking neural networks publication-title: Neural Computation – reference: O’Connor, P., & Welling, M. (2016). Deep spiking networks, arXiv preprint – start-page: 555 year: 2017 end-page: 577 ident: b13 article-title: STDP-compatible approximation of backpropagation in an energy-based model publication-title: Neural Computation – volume: 95 start-page: 552 year: 2005 end-page: 558 ident: b20 article-title: A gradient descent rule for spiking neurons emitting multiple spikes publication-title: Information Processing Letters – reference: , 99. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b115 article-title: Deep learning publication-title: Nature – volume: 381 start-page: 607 year: 1996 end-page: 609 ident: b170 article-title: Emergence of simple-cell receptive field properties by learning a sparse code for natural images publication-title: Nature – start-page: 299 year: 2016 end-page: 306 ident: b174 article-title: Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition publication-title: International conference on neural networks – start-page: 1 year: 2010 end-page: 8 ident: b144 article-title: Learning to recognize objects using waves of spikes and spike timing-dependent plasticity publication-title: Neural Networks, The 2010 international joint conference on – volume: 10 year: 2014 ident: b90 article-title: STDP installs in winner-take-all circuits an online approximation to hidden Markov model learning publication-title: PLoS Computational Biology – start-page: 1117 year: 2015 end-page: 1125 ident: b47 article-title: Backpropagation for energy-efficient neuromorphic computing publication-title: Advances in neural information processing systems – start-page: 1096 year: 2009 end-page: 1104 ident: b122 article-title: Unsupervised feature learning for audio classification using convolutional deep belief networks publication-title: Advances in neural information processing systems – volume: 7 year: 2011 ident: b23 article-title: Neural dynamics as sampling: A model for stochastic computation in recurrent networks of spiking neurons publication-title: PLoS Computational Biology – volume: 37 start-page: 3327 year: 1997 end-page: 3338 ident: b9 article-title: The “independent components” of natural scenes are edge filters publication-title: Vision Research – reference: (pp. 580–587). – volume: 35 start-page: 2706 year: 2013 end-page: 2719 ident: b177 article-title: Mapping from frame-driven to frame-free event-driven vision systems by low-rate rate-coding and coincidence processing. application to feed forward convnets publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – year: 2017 ident: b234 article-title: A novel data-driven model for real-time influenza forecasting publication-title: bioRxiv – volume: 90 start-page: 211 year: 2018 end-page: 220 ident: b227 article-title: Training a hidden Markov model with a Bayesian spiking neural network publication-title: Journal of Signal Processing Systems – volume: 11 year: 2015 ident: b24 article-title: Mirrored STDP implements autoencoder learning in a network of spiking neurons publication-title: PLoS Computational Biology – year: 1991 ident: b70 article-title: Introduction to the theory of neural computation – volume: 99 start-page: 56 year: 2018 end-page: 67 ident: b98 article-title: STDP-based spiking deep convolutional neural networks for object recognition publication-title: Neural Networks – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: b195 article-title: ImageNet large scale visual recognition challenge publication-title: International Journal of Computer Vision – volume: 8 start-page: 142 year: 2017 ident: b233 article-title: Perception science in the age of deep neural networks publication-title: Frontiers in Psychology – volume: 95 start-page: 245 year: 2017 end-page: 258 ident: b67 article-title: Neuroscience-inspired artificial intelligence publication-title: Neuron – volume: 33 start-page: 11515 year: 2013 end-page: 11529 ident: b103 article-title: Emergence of dynamic memory traces in cortical microcircuit models through STDP publication-title: The Journal of Neuroscience – year: 2016 ident: b61 article-title: Deep learning – volume: 22 year: 2012 ident: b152 article-title: Span: Spike pattern association neuron for learning spatio-temporal spike patterns publication-title: International Journal of Neural Systems – reference: Lamb, A., Goyal, A., Zhang, Y., Zhang, S., Courville, A., & Bengio, Y. (2016). Professor forcing: A new algorithm for training recurrent networks, arXiv preprint – reference: Hunsberger, E., & Eliasmith, C. (2016). Training spiking deep networks for neuromorphic hardware, arXiv preprint – volume: 61 start-page: 85 year: 2015 end-page: 117 ident: b200 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks – volume: 97 year: 2018 ident: b8 article-title: Phase diagram of restricted Boltzmann machines and generalized Hopfield networks with arbitrary priors publication-title: Physical Review E – start-page: 2282 year: 2016 end-page: 2285 ident: b163 article-title: Effective sensor fusion with event-based sensors and deep network architectures publication-title: Circuits and systems, 2016 IEEE international symposium on – volume: 26 start-page: 365 year: 2012 end-page: 371 ident: b131 article-title: Reservoir computing trends publication-title: KI-Künstliche Intelligenz – year: 2002 ident: b185 article-title: Probabilistic models of the brain: Perception and neural function – volume: 9 start-page: 1 year: 2015 end-page: 14 ident: b213 article-title: Robustness of spiking deep belief networks to noise and reduced bit precision of neuro-inspired hardware platforms publication-title: Frontiers in Neuroscience – reference: Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint – volume: 338 start-page: 1202 year: 2012 end-page: 1205 ident: b44 article-title: A large-scale model of the functioning brain publication-title: Science – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: b73 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation – start-page: 1 year: 2014 end-page: 12 ident: b203 article-title: Hierarchical models of the visual system publication-title: Encyclopedia of computational neuroscience – volume: 6 year: 2016 ident: b100 article-title: Deep networks can resemble human feed-forward vision in invariant object recognition publication-title: Scientific Reports – volume: 9 start-page: 437 year: 2015 ident: b172 article-title: Converting static image datasets to spiking neuromorphic datasets using saccades publication-title: Frontiers in Neuroscience – volume: 19 start-page: 1437 year: 2007 end-page: 1467 ident: b154 article-title: Spike-timing-dependent plasticity in balanced random networks publication-title: Neural Computation – year: 2014 ident: b55 article-title: Neuronal dynamics: From single neurons to networks and models of cognition – volume: 20 start-page: 14 year: 2012 end-page: 22 ident: b151 article-title: Acoustic modeling using deep belief networks publication-title: IEEE Transactions on Audio, Speech, and Language Processing – reference: Bengio, Y., Lee, D. -H., Bornschein, J., Mesnard, T., & Lin, Z. (2015). Towards biologically plausible deep learning, arXiv preprint – start-page: 234 year: 2012 end-page: 260 ident: b91 article-title: Evolving spiking neural networks and neurogenetic systems for spatio-and spectro-temporal data modelling and pattern recognition publication-title: Advances in computational intelligence – volume: 20 start-page: 1631 year: 2008 end-page: 1649 ident: b113 article-title: Representational power of restricted boltzmann machines and deep belief networks publication-title: Neural Computation – reference: , 1–9. – volume: 21 start-page: 1259 year: 2009 end-page: 1276 ident: b141 article-title: Competitive STDP-based spike pattern learning publication-title: Neural computation – year: 2003 ident: b237 article-title: Spiking neural networks, an introduction – reference: , 1–14. – volume: 58 start-page: 365 year: 2004 end-page: 371 ident: b173 article-title: Spike-timing-dependent synaptic plasticity: From single spikes to spike trains publication-title: Neurocomputing – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: b11 article-title: Learning deep architectures for AI publication-title: Foundations and Trends in Machine Learning – volume: 32 start-page: 1133 year: 2008 end-page: 1147 ident: b158 article-title: Optimal predictions in everyday cognition: The wisdom of individuals or crowds? publication-title: Cognitive Science – reference: Bellec, G., Salaj, D., Subramoney, A., Legenstein, R., & Maass, W. (2018). Long short-term memory and learning-to-learn in networks of spiking neurons, arXiv preprint – volume: 14 start-page: 1569 year: 2003 end-page: 1572 ident: b85 article-title: Simple model of spiking neurons publication-title: IEEE Transactions on Neural Networks – reference: Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In – volume: 4 start-page: 1 year: 2015 end-page: 8 ident: b220 article-title: A minimal spiking neural network to rapidly train and classify handwritten digits in binary and 10-digit tasks publication-title: International Journal of Advanced Research in Artificial Intelligence – volume: 10 start-page: 92 year: 2016 ident: b99 article-title: Humans and deep networks largely agree on which kinds of variation make object recognition harder publication-title: Frontiers in Computational Neuroscience – start-page: 400 year: 2015 end-page: 411 ident: b149 article-title: Rough deep belief network-application to incomplete handwritten digits pattern classification publication-title: International conference on information and software technologies – volume: 18 start-page: 1318 year: 2006 end-page: 1348 ident: b180 article-title: Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning publication-title: Neural Computation – volume: 268 start-page: 1503 year: 1995 end-page: 1506 ident: b136 article-title: Reliability of spike timing in neocortical neurons publication-title: Science – volume: 105 start-page: 294 year: 2018 end-page: 303 ident: b230 article-title: Representation learning using event-based STDP publication-title: Neural Networks – year: 2007 ident: b43 article-title: Bayesian brain: Probabilistic approaches to neural coding – volume: 12 start-page: 288 year: 2013 end-page: 295 ident: b184 article-title: Immunity to device variations in a spiking neural network with memristive nanodevices publication-title: IEEE Transactions on Nanotechnology – volume: 22 start-page: 467 year: 2010 end-page: 510 ident: b181 article-title: Supervised learning in spiking neural networks with ReSuMe: Sequence learning, classification, and spike shifting publication-title: Neural Computation – volume: 22 start-page: 1419 year: 2009 end-page: 1431 ident: b57 article-title: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection publication-title: Neural Networks – volume: 20 start-page: 5392 year: 2000 end-page: 5400 ident: b188 article-title: Temporal coding of visual information in the thalamus publication-title: Journal of Neuroscience – volume: 1 start-page: 1 year: 1991 end-page: 47 ident: b49 article-title: Distributed hierarchical processing in the primate cerebral cortex publication-title: Cerebral Cortex – start-page: 1097 year: 2012 end-page: 1105 ident: b107 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in neural information processing systems – volume: 205 start-page: 382 year: 2016 end-page: 392 ident: b97 article-title: Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition publication-title: Neurocomputing – year: 2008 ident: b215 article-title: Generating facial expressions with deep belief nets publication-title: Affective computing – year: 2016 ident: b48 article-title: Convolutional networks for fast, energy-efficient neuromorphic computing publication-title: Proceedings of the National Academy of Sciences – volume: 3 start-page: 919 year: 2000 end-page: 926 ident: b208 article-title: Competitive Hebbian learning through spike-timing-dependent synaptic plasticity publication-title: Nature Neuroscience – volume: 23 start-page: 819 year: 2010 end-page: 835 ident: b242 article-title: Evolving spiking neural networks for audiovisual information processing publication-title: Neural Networks – reference: (pp. 3889–3897). – volume: 117 start-page: 500 year: 1952 end-page: 544 ident: b76 article-title: A quantitative description of membrane current and its application to conduction and excitation in nerve publication-title: The Journal of Physiology – reference: (pp. 1717–1724). – start-page: 899 year: 2017 end-page: 908 ident: b223 article-title: Bio-inspired multi-layer spiking neural network extracts discriminative features from speech signals publication-title: International conference on neural information processing – volume: 9 start-page: 420 year: 2006 end-page: 428 ident: b64 article-title: The tempotron: A neuron that learns spike timing-based decisions publication-title: Nature Neuroscience – volume: 437 start-page: 1027 year: 2005 ident: b127 article-title: Repeated cocaine exposure in vivo facilitates LTP induction in midbrain dopamine neurons publication-title: Nature – start-page: ENEURO year: 2016 end-page: 0048 ident: b176 article-title: Learning probabilistic inference through STDP publication-title: eneuro – volume: 144 start-page: 526 year: 2014 end-page: 536 ident: b239 article-title: An online supervised learning method for spiking neural networks with adaptive structure publication-title: Neurocomputing – volume: 48 start-page: 17 year: 2002 end-page: 37 ident: b18 article-title: Error-backpropagation in temporally encoded networks of spiking neurons publication-title: Neurocomputing – volume: Vol. 3 start-page: 2175 year: 1998 end-page: 2179 ident: b123 article-title: Robust speech recognition with dynamic synapses publication-title: Neural networks proceedings, 1998. IEEE world congress on computational intelligence. The 1998 IEEE international joint conference on – start-page: 4277 year: 2012 end-page: 4280 ident: b2 article-title: Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition publication-title: Acoustics, speech and signal processing, 2012 IEEE international conference on – volume: 33 start-page: 5475 year: 2013 end-page: 5485 ident: b101 article-title: Inhibitory interneurons decorrelate excitatory cells to drive sparse code formation in a spiking model of V1 publication-title: Journal of Neuroscience – volume: 10 start-page: 508 year: 2016 ident: b119 article-title: Training deep spiking neural networks using backpropagation publication-title: Frontiers in Neuroscience – start-page: 234 year: 2015 end-page: 241 ident: b191 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: International conference on medical image computing and computer-assisted intervention – volume: 219 start-page: 197 year: 2013 end-page: 207 ident: b209 article-title: Asynchronous spiking neural P systems with local synchronization publication-title: Information Sciences – volume: 7 year: 2011 ident: b248 article-title: A sparse coding model with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptive fields publication-title: PLoS Computational Biology – volume: 103 start-page: 2219 year: 2015 end-page: 2224 ident: b134 article-title: To spike or not to spike: That is the question publication-title: Proceedings of the IEEE – volume: 12 start-page: 42 year: 2018 ident: b175 article-title: A retinotopic spiking neural network system for accurate recognition of moving objects using NeuCube and dynamic vision sensors publication-title: Frontiers in Computational Neuroscience – volume: 19 start-page: 295 year: 2009 end-page: 308 ident: b58 article-title: Spiking neural networks publication-title: International Journal of Neural Systems – year: 2001 ident: b36 article-title: Theoretical neuroscience: Computational and mathematical modeling of neural systems – volume: 32 start-page: 131 year: 2010 end-page: 146 ident: b145 article-title: Segmentation and edge detection based on spiking neural network model publication-title: Neural Processing Letters – year: 2018 ident: b211 article-title: Principles of neural information theory: Computational neuroscience and metabolic efficiency – volume: 19 start-page: 2881 year: 2007 end-page: 2912 ident: b21 article-title: Learning real-world stimuli in a neural network with spike-driven synaptic dynamics publication-title: Neural Computation – reference: (pp. 770–778). – volume: 168 start-page: 413 year: 2017 end-page: 426 ident: b207 article-title: Cellular and circuit mechanisms shaping the perceptual properties of the primate fovea publication-title: Cell – volume: 3 year: 2008 ident: b140 article-title: Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains publication-title: PloS One – reference: Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv preprint – start-page: 136 year: 2011 end-page: 144 ident: b189 article-title: Variational learning for recurrent spiking networks publication-title: Advances in neural information processing systems – reference: Krizhevsky, A., & Hinton, G. (2010). Convolutional deep belief networks on CIFAR-10, Unpublished Manuscript 40. – volume: 11 start-page: 682 year: 2017 ident: b193 article-title: Conversion of continuous-valued deep networks to efficient event-driven networks for image classification publication-title: Frontiers in Neuroscience – volume: 32 start-page: i121 year: 2016 end-page: i127 ident: b245 article-title: Convolutional neural network architectures for predicting DNA–protein binding publication-title: Bioinformatics – volume: 34 start-page: 1537 year: 2015 end-page: 1557 ident: b3 article-title: Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip publication-title: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems – start-page: 1 year: 2017 end-page: 9 ident: b155 article-title: Supervised learning based on temporal coding in spiking neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 113 start-page: 54 year: 2015 end-page: 66 ident: b26 article-title: Spiking deep convolutional neural networks for energy-efficient object recognition publication-title: International Journal of Computer Vision – volume: 138 start-page: 3 year: 2014 end-page: 13 ident: b243 article-title: A brain-inspired spiking neural network model with temporal encoding and learning publication-title: Neurocomputing – volume: 14 start-page: 187 year: 2007 end-page: 212 ident: b56 article-title: Improved spiking neural networks for EEG classification and epilepsy and seizure detection publication-title: Integrated Computer-Aided Engineering – reference: , 1–16. – year: 2015 ident: b216 article-title: Going deeper with convolutions – volume: 41 start-page: 188 year: 2013 end-page: 201 ident: b94 article-title: Dynamic evolving spiking neural networks for on-line spatio-and spectro-temporal pattern recognition publication-title: Neural Networks – volume: 3 start-page: 127 year: 2009 end-page: 149 ident: b130 article-title: Reservoir computing approaches to recurrent neural network training publication-title: Computer Science Review – volume: 7 year: 2012 ident: b50 article-title: The chronotron: A neuron that learns to fire temporally precise spike patterns publication-title: PloS One – volume: 10 start-page: 1659 year: 1997 end-page: 1671 ident: b133 article-title: Networks of spiking neurons: The third generation of neural network models publication-title: Neural networks – start-page: 1 year: 2016 end-page: 10 ident: b124 article-title: Randome synaptic feedback weights support error backpropagation for deep learning publication-title: Nature Communications – volume: 8 start-page: 1 year: 1996 end-page: 40 ident: b132 article-title: Lower bounds for the computational power of networks of spiking neurons publication-title: Neural Computation – volume: 437 start-page: 1027 issue: 7061 year: 2005 ident: 10.1016/j.neunet.2018.12.002_b127 article-title: Repeated cocaine exposure in vivo facilitates LTP induction in midbrain dopamine neurons publication-title: Nature doi: 10.1038/nature04050 – volume: 26 start-page: 365 issue: 4 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b131 article-title: Reservoir computing trends publication-title: KI-Künstliche Intelligenz doi: 10.1007/s13218-012-0204-5 – volume: 7 start-page: 1 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b168 article-title: Real-time classification and sensor fusion with a spiking deep belief network publication-title: Frontiers in Neuroscience – start-page: 234 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b191 article-title: U-net: Convolutional networks for biomedical image segmentation – volume: 13 start-page: 426 issue: 2 year: 2002 ident: 10.1016/j.neunet.2018.12.002_b19 article-title: Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.991428 – volume: Vol. 1 start-page: 39 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b150 article-title: Deep belief networks for phone recognition – volume: 14 start-page: 179 issue: 2 year: 1990 ident: 10.1016/j.neunet.2018.12.002_b45 article-title: Finding structure in time publication-title: Cognitive Science doi: 10.1207/s15516709cog1402_1 – volume: 79 start-page: 2554 issue: 8 year: 1982 ident: 10.1016/j.neunet.2018.12.002_b77 article-title: Neural networks and physical systems with emergent collective computational abilities publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.79.8.2554 – start-page: 2282 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b163 article-title: Effective sensor fusion with event-based sensors and deep network architectures – volume: 58 start-page: 365 year: 2004 ident: 10.1016/j.neunet.2018.12.002_b173 article-title: Spike-timing-dependent synaptic plasticity: From single spikes to spike trains publication-title: Neurocomputing doi: 10.1016/j.neucom.2004.01.068 – volume: 26 start-page: 1963 issue: 9 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b247 article-title: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2014.2362542 – start-page: 145 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b228 article-title: Towards recognition of protein function based on its structure using deep convolutional networks – ident: 10.1016/j.neunet.2018.12.002_b217 doi: 10.1109/CVPR.2016.308 – volume: 3 start-page: 195 issue: 2 year: 2004 ident: 10.1016/j.neunet.2018.12.002_b17 article-title: The evidence for neural information processing with precise spike-times: A survey publication-title: Natural Computing doi: 10.1023/B:NACO.0000027755.02868.60 – volume: 3 start-page: 127 issue: 3 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b130 article-title: Reservoir computing approaches to recurrent neural network training publication-title: Computer Science Review doi: 10.1016/j.cosrev.2009.03.005 – volume: 64 start-page: 165 issue: 2 year: 1990 ident: 10.1016/j.neunet.2018.12.002_b51 article-title: Forming sparse representations by local anti-hebbian learning publication-title: Biological Cybernetics doi: 10.1007/BF02331346 – ident: 10.1016/j.neunet.2018.12.002_b240 – start-page: 53 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b63 article-title: Character recognition using spiking neural networks – start-page: 1 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b144 article-title: Learning to recognize objects using waves of spikes and spike timing-dependent plasticity – ident: 10.1016/j.neunet.2018.12.002_b41 doi: 10.1109/ICRC.2016.7738691 – year: 2015 ident: 10.1016/j.neunet.2018.12.002_b216 – volume: 31 start-page: 25 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b27 article-title: Spike timing-dependent plasticity: A Hebbian learning rule publication-title: Annual Review of Neuroscience doi: 10.1146/annurev.neuro.31.060407.125639 – volume: 19 start-page: 1437 issue: 6 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b154 article-title: Spike-timing-dependent plasticity in balanced random networks publication-title: Neural Computation doi: 10.1162/neco.2007.19.6.1437 – volume: 26 start-page: 989 year: 1999 ident: 10.1016/j.neunet.2018.12.002_b37 article-title: SpikeNET: A simulator for modeling large networks of integrate and fire neurons publication-title: Neurocomputing doi: 10.1016/S0925-2312(99)00095-8 – ident: 10.1016/j.neunet.2018.12.002_b82 – volume: 9 start-page: 420 issue: 3 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b64 article-title: The tempotron: A neuron that learns spike timing-based decisions publication-title: Nature Neuroscience doi: 10.1038/nn1643 – volume: 138 start-page: 3 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b243 article-title: A brain-inspired spiking neural network model with temporal encoding and learning publication-title: Neurocomputing doi: 10.1016/j.neucom.2013.06.052 – year: 2001 ident: 10.1016/j.neunet.2018.12.002_b36 – volume: 113 start-page: 54 issue: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b26 article-title: Spiking deep convolutional neural networks for energy-efficient object recognition publication-title: International Journal of Computer Vision doi: 10.1007/s11263-014-0788-3 – year: 1991 ident: 10.1016/j.neunet.2018.12.002_b70 – volume: 11 issue: 12 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b24 article-title: Mirrored STDP implements autoencoder learning in a network of spiking neurons publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1004566 – volume: 22 start-page: 467 issue: 2 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b181 article-title: Supervised learning in spiking neural networks with ReSuMe: Sequence learning, classification, and spike shifting publication-title: Neural Computation doi: 10.1162/neco.2009.11-08-901 – start-page: 81 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b225 article-title: Multi-layer unsupervised learning in a spiking convolutional neural network – volume: 95 start-page: 552 issue: 6 year: 2005 ident: 10.1016/j.neunet.2018.12.002_b20 article-title: A gradient descent rule for spiking neurons emitting multiple spikes publication-title: Information Processing Letters doi: 10.1016/j.ipl.2005.05.023 – volume: 32 start-page: 131 issue: 2 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b145 article-title: Segmentation and edge detection based on spiking neural network model publication-title: Neural Processing Letters doi: 10.1007/s11063-010-9149-6 – volume: 51 start-page: 793 issue: 9 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b108 article-title: Towards a neurocomputational model of speech production and perception publication-title: Speech Communication doi: 10.1016/j.specom.2008.08.002 – ident: 10.1016/j.neunet.2018.12.002_b83 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.neunet.2018.12.002_b116 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE doi: 10.1109/5.726791 – year: 2017 ident: 10.1016/j.neunet.2018.12.002_b210 article-title: Motor control by precisely timed spike patterns publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.1611734114 – start-page: 160 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b199 article-title: Reservoir-based evolving spiking neural network for spatio-temporal pattern recognition – ident: 10.1016/j.neunet.2018.12.002_b129 doi: 10.1109/CVPR.2015.7298965 – volume: 32 start-page: 1133 issue: 7 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b158 article-title: Optimal predictions in everyday cognition: The wisdom of individuals or crowds? publication-title: Cognitive Science doi: 10.1080/03640210802353016 – start-page: 1096 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b122 article-title: Unsupervised feature learning for audio classification using convolutional deep belief networks – volume: 2 start-page: 1 issue: 1 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b11 article-title: Learning deep architectures for AI publication-title: Foundations and Trends in Machine Learning doi: 10.1561/2200000006 – volume: 11 start-page: 350 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b214 article-title: An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2017.00350 – ident: 10.1016/j.neunet.2018.12.002_b206 – volume: 9 start-page: 1015 issue: 5 year: 1997 ident: 10.1016/j.neunet.2018.12.002_b102 article-title: Reduction of the Hodgkin-Huxley equations to a single-variable threshold model publication-title: Neural Computation doi: 10.1162/neco.1997.9.5.1015 – ident: 10.1016/j.neunet.2018.12.002_b171 doi: 10.1109/CVPR.2014.222 – ident: 10.1016/j.neunet.2018.12.002_b194 – ident: 10.1016/j.neunet.2018.12.002_b12 – volume: 29 start-page: 82 issue: 6 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b72 article-title: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2012.2205597 – volume: 48 start-page: 109 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b15 article-title: Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule publication-title: Neural Networks doi: 10.1016/j.neunet.2013.07.012 – volume: 134 start-page: 269 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b95 article-title: Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke publication-title: Neurocomputing doi: 10.1016/j.neucom.2013.09.049 – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b4 article-title: Normad-normalized approximate descent based supervised learning rule for spiking neurons – start-page: 299 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b174 article-title: Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition – volume: 148 start-page: 574 issue: 3 year: 1959 ident: 10.1016/j.neunet.2018.12.002_b79 article-title: Receptive fields of single neurones in the cat’s striate cortex publication-title: The Journal of Physiology doi: 10.1113/jphysiol.1959.sp006308 – volume: 54 start-page: 95 issue: 10 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b121 article-title: Unsupervised learning of hierarchical representations with convolutional deep belief networks publication-title: Communications of the ACM doi: 10.1145/2001269.2001295 – volume: 22 start-page: 2621 issue: 12 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b162 article-title: Minitaur, an event-driven FPGA-based spiking network accelerator publication-title: IEEE Transactions on Very Large Scale Integration (VLSI) Systems doi: 10.1109/TVLSI.2013.2294916 – start-page: 631 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b205 article-title: A spike-based long short-term memory on a neurosynaptic processor – volume: 9 start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b213 article-title: Robustness of spiking deep belief networks to noise and reduced bit precision of neuro-inspired hardware platforms publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2015.00222 – volume: 17 start-page: 859 issue: 4 year: 2005 ident: 10.1016/j.neunet.2018.12.002_b65 article-title: Neurons tune to the earliest spikes through STDP publication-title: Neural Computation doi: 10.1162/0899766053429390 – volume: 30 start-page: 1514 issue: 6 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b246 article-title: SuperSpike: Supervised learning in multi-layer spiking neural networks publication-title: Neural Computation doi: 10.1162/neco_a_01086 – volume: 117 start-page: 500 issue: 4 year: 1952 ident: 10.1016/j.neunet.2018.12.002_b76 article-title: A quantitative description of membrane current and its application to conduction and excitation in nerve publication-title: The Journal of Physiology doi: 10.1113/jphysiol.1952.sp004764 – start-page: 899 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b223 article-title: Bio-inspired multi-layer spiking neural network extracts discriminative features from speech signals – volume: 34 start-page: 1537 issue: 10 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b3 article-title: Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip publication-title: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems doi: 10.1109/TCAD.2015.2474396 – ident: 10.1016/j.neunet.2018.12.002_b81 – volume: 18 start-page: 851 issue: 5 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b148 article-title: Deep learning in bioinformatics publication-title: Briefings in Bioinformatics – volume: 37 start-page: 3327 issue: 23 year: 1997 ident: 10.1016/j.neunet.2018.12.002_b9 article-title: The “independent components” of natural scenes are edge filters publication-title: Vision Research doi: 10.1016/S0042-6989(97)00121-1 – volume: 22 start-page: 79 issue: 1 year: 1951 ident: 10.1016/j.neunet.2018.12.002_b109 article-title: On information and sufficiency publication-title: The Annals of Mathematical Statistics doi: 10.1214/aoms/1177729694 – volume: 449 start-page: 92 issue: 7158 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b25 article-title: Temporal precision in the neural code and the timescales of natural vision publication-title: Nature doi: 10.1038/nature06105 – volume: Vol. 656 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b71 article-title: How to do backpropagation in a brain – start-page: 1 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b219 article-title: Training spiking convnets by STDP and Gradient Descent – volume: 391 start-page: 245 year: 1998 ident: 10.1016/j.neunet.2018.12.002_b34 article-title: Constrains on cortical and thalamic projections: The no-strong-loops hypothesis publication-title: Nature doi: 10.1038/34584 – ident: 10.1016/j.neunet.2018.12.002_b106 – volume: 144 start-page: 526 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b239 article-title: An online supervised learning method for spiking neural networks with adaptive structure publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.04.017 – volume: 14 start-page: 187 issue: 3 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b56 article-title: Improved spiking neural networks for EEG classification and epilepsy and seizure detection publication-title: Integrated Computer-Aided Engineering doi: 10.3233/ICA-2007-14301 – volume: 9 issue: 4 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b166 article-title: Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1003037 – volume: 118 issue: 1 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b182 article-title: Spatiotemporal dynamics and reliable computations in recurrent spiking neural networks publication-title: Physical Review Letters doi: 10.1103/PhysRevLett.118.018103 – ident: 10.1016/j.neunet.2018.12.002_b118 – volume: 137 start-page: 47 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b110 article-title: Time series forecasting using a deep belief network with restricted Boltzmann machines publication-title: Neurocomputing doi: 10.1016/j.neucom.2013.03.047 – ident: 10.1016/j.neunet.2018.12.002_b112 – volume: 40 start-page: 1063 issue: 6 year: 2003 ident: 10.1016/j.neunet.2018.12.002_b204 article-title: Learning in spiking neural networks by reinforcement of stochastic synaptic transmission publication-title: Neuron doi: 10.1016/S0896-6273(03)00761-X – volume: 38 start-page: 1346 issue: 7 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b111 article-title: HOTS: A hierarchy of event-based time-surfaces for pattern recognition publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2016.2574707 – volume: 44 start-page: 937 year: 2002 ident: 10.1016/j.neunet.2018.12.002_b159 article-title: Speech recognition with spiking neurons and dynamic synapses: A model motivated by the human auditory pathway publication-title: Neurocomputing doi: 10.1016/S0925-2312(02)00494-0 – year: 2011 ident: 10.1016/j.neunet.2018.12.002_b192 – volume: 115 start-page: 211 issue: 3 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b195 article-title: ImageNet large scale visual recognition challenge publication-title: International Journal of Computer Vision doi: 10.1007/s11263-015-0816-y – volume: 7 issue: 10 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b248 article-title: A sparse coding model with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptive fields publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1002250 – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b40 article-title: Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing – year: 2008 ident: 10.1016/j.neunet.2018.12.002_b215 article-title: Generating facial expressions with deep belief nets – volume: 103 start-page: 2219 issue: 12 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b134 article-title: To spike or not to spike: That is the question publication-title: Proceedings of the IEEE doi: 10.1109/JPROC.2015.2496679 – volume: 48 start-page: 17 issue: 1 year: 2002 ident: 10.1016/j.neunet.2018.12.002_b18 article-title: Error-backpropagation in temporally encoded networks of spiking neurons publication-title: Neurocomputing doi: 10.1016/S0925-2312(01)00658-0 – start-page: 873 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b120 article-title: Sparse deep belief net model for visual area V2 – year: 2007 ident: 10.1016/j.neunet.2018.12.002_b43 – start-page: 1 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b229 article-title: Acquisition of visual features through probabilistic spike timing dependent plasticity – volume: 15 start-page: 585 issue: 5 year: 2005 ident: 10.1016/j.neunet.2018.12.002_b235 article-title: Spike train metrics publication-title: Current Opinion in Neurobiology doi: 10.1016/j.conb.2005.08.002 – volume: Vol. 3 start-page: 2175 year: 1998 ident: 10.1016/j.neunet.2018.12.002_b123 article-title: Robust speech recognition with dynamic synapses – start-page: 846 year: 2003 ident: 10.1016/j.neunet.2018.12.002_b87 article-title: The spike response model: A framework to predict neuronal spike trains – ident: 10.1016/j.neunet.2018.12.002_b31 – volume: 61 start-page: 85 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b200 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks doi: 10.1016/j.neunet.2014.09.003 – start-page: 8012 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b89 article-title: Multi-distribution deep belief network for speech synthesis – volume: 20 start-page: 5392 issue: 14 year: 2000 ident: 10.1016/j.neunet.2018.12.002_b188 article-title: Temporal coding of visual information in the thalamus publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.20-14-05392.2000 – ident: 10.1016/j.neunet.2018.12.002_b117 – volume: 44 issue: 11 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b183 article-title: DanQ: A hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences publication-title: Nucleic Acids Research doi: 10.1093/nar/gkw226 – volume: 9 start-page: 437 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b172 article-title: Converting static image datasets to spiking neuromorphic datasets using saccades publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2015.00437 – ident: 10.1016/j.neunet.2018.12.002_b222 – volume: 18 start-page: 1527 issue: 7 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b73 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation doi: 10.1162/neco.2006.18.7.1527 – volume: 32 start-page: i121 issue: 12 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b245 article-title: Convolutional neural network architectures for predicting DNA–protein binding publication-title: Bioinformatics doi: 10.1093/bioinformatics/btw255 – volume: 52 start-page: 62 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b92 article-title: NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data publication-title: Neural Networks doi: 10.1016/j.neunet.2014.01.006 – year: 1999 ident: 10.1016/j.neunet.2018.12.002_b190 – start-page: 1 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b203 article-title: Hierarchical models of the visual system – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b212 article-title: Scalable energy-efficient, low-latency implementations of trained spiking deep belief networks on spinnaker – start-page: 272 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b33 article-title: Cortical microcircuits as gated-recurrent neural networks – year: 2016 ident: 10.1016/j.neunet.2018.12.002_b48 article-title: Convolutional networks for fast, energy-efficient neuromorphic computing publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.1604850113 – volume: 22 start-page: 1419 issue: 10 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b57 article-title: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection publication-title: Neural Networks doi: 10.1016/j.neunet.2009.04.003 – start-page: 1117 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b47 article-title: Backpropagation for energy-efficient neuromorphic computing – volume: 4 start-page: 1 issue: 7 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b220 article-title: A minimal spiking neural network to rapidly train and classify handwritten digits in binary and 10-digit tasks publication-title: International Journal of Advanced Research in Artificial Intelligence doi: 10.14569/IJARAI.2015.040701 – volume: 240 start-page: 191 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b224 article-title: A spiking network that learns to extract spike signatures from speech signals publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.01.088 – ident: 10.1016/j.neunet.2018.12.002_b156 – volume: 6 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b100 article-title: Deep networks can resemble human feed-forward vision in invariant object recognition publication-title: Scientific Reports doi: 10.1038/srep32672 – volume: 41 start-page: 188 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b94 article-title: Dynamic evolving spiking neural networks for on-line spatio-and spectro-temporal pattern recognition publication-title: Neural Networks doi: 10.1016/j.neunet.2012.11.014 – volume: 11 issue: 23–63 year: 1987 ident: 10.1016/j.neunet.2018.12.002_b62 article-title: Competitive learning: From interactive activation to adaptive resonance publication-title: Cognitive Science – year: 2014 ident: 10.1016/j.neunet.2018.12.002_b55 – year: 2003 ident: 10.1016/j.neunet.2018.12.002_b237 – start-page: 555 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b13 article-title: STDP-compatible approximation of backpropagation in an energy-based model publication-title: Neural Computation doi: 10.1162/NECO_a_00934 – start-page: 400 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b149 article-title: Rough deep belief network-application to incomplete handwritten digits pattern classification – volume: 23 start-page: 819 issue: 7 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b242 article-title: Evolving spiking neural networks for audiovisual information processing publication-title: Neural Networks doi: 10.1016/j.neunet.2010.04.009 – volume: 8 start-page: 142 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b233 article-title: Perception science in the age of deep neural networks publication-title: Frontiers in Psychology doi: 10.3389/fpsyg.2017.00142 – volume: 96 issue: 4 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b7 article-title: Phase transitions in restricted Boltzmann machines with generic priors publication-title: Physical Review E doi: 10.1103/PhysRevE.96.042156 – volume: 22 start-page: 135 issue: 2 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b187 article-title: A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields publication-title: Journal of Computational Neuroscience doi: 10.1007/s10827-006-0003-9 – year: 2017 ident: 10.1016/j.neunet.2018.12.002_b234 article-title: A novel data-driven model for real-time influenza forecasting publication-title: bioRxiv – year: 2013 ident: 10.1016/j.neunet.2018.12.002_b88 – volume: 18 start-page: 1318 issue: 6 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b180 article-title: Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning publication-title: Neural Computation doi: 10.1162/neco.2006.18.6.1318 – volume: 7 issue: 8 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b50 article-title: The chronotron: A neuron that learns to fire temporally precise spike patterns publication-title: PloS One doi: 10.1371/journal.pone.0040233 – volume: 107 start-page: 3 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b153 article-title: Training spiking neural networks to associate spatio-temporal input-output spike patterns publication-title: Neurocomputing doi: 10.1016/j.neucom.2012.08.034 – volume: 8 start-page: 127 issue: 2 year: 1997 ident: 10.1016/j.neunet.2018.12.002_b236 article-title: Metric-space analysis of spike trains: Theory, algorithms and application publication-title: Network. Computation in Neural Systems doi: 10.1088/0954-898X_8_2_003 – volume: 330 start-page: 845 issue: 6005 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b52 article-title: Functional compartmentalization and viewpoint generalization within the macaque face-processing system publication-title: Science doi: 10.1126/science.1194908 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b115 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: 10.1016/j.neunet.2018.12.002_b68 doi: 10.1109/CVPR.2016.90 – start-page: 1 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b157 article-title: First-spike based visual categorization using reward-modulated STDP publication-title: IEEE Transactions on Neural Networks and Learning Systems – start-page: 1 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b124 article-title: Randome synaptic feedback weights support error backpropagation for deep learning publication-title: Nature Communications – volume: 3 start-page: 1 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b139 article-title: A history of spike-timing-dependent plasticity publication-title: Frontiers in Synaptic Neuroscience doi: 10.3389/fnsyn.2011.00004 – start-page: 4277 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b2 article-title: Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition – volume: 70 start-page: 1297 issue: 11 year: 1980 ident: 10.1016/j.neunet.2018.12.002_b138 article-title: Mathematical description of the responses of simple cortical cells publication-title: Journal of the Optical Society of America doi: 10.1364/JOSA.70.001297 – start-page: 1097 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b107 article-title: Imagenet classification with deep convolutional neural networks – start-page: 1 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b146 article-title: A digital neurosynaptic core using embedded crossbar memory with 45pj per spike in 45nm – year: 2002 ident: 10.1016/j.neunet.2018.12.002_b54 – ident: 10.1016/j.neunet.2018.12.002_b10 – ident: 10.1016/j.neunet.2018.12.002_b59 doi: 10.1109/CVPR.2014.81 – volume: 20 start-page: 14 issue: 1 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b151 article-title: Acoustic modeling using deep belief networks publication-title: IEEE Transactions on Audio, Speech, and Language Processing doi: 10.1109/TASL.2011.2109382 – start-page: 136 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b189 article-title: Variational learning for recurrent spiking networks – volume: 33 start-page: 11515 issue: 28 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b103 article-title: Emergence of dynamic memory traces in cortical microcircuit models through STDP publication-title: The Journal of Neuroscience doi: 10.1523/JNEUROSCI.5044-12.2013 – start-page: 1 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b155 article-title: Supervised learning based on temporal coding in spiking neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2017.2726060 – volume: 19 start-page: 295 issue: 04 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b58 article-title: Spiking neural networks publication-title: International Journal of Neural Systems doi: 10.1142/S0129065709002002 – year: 1995 ident: 10.1016/j.neunet.2018.12.002_b16 – start-page: 450 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b126 article-title: MT-spike: A multilayer time-based spiking neuromorphic architecture with temporal error backpropagation – volume: 376 start-page: 33 issue: 6535 year: 1995 ident: 10.1016/j.neunet.2018.12.002_b78 article-title: Pattern recognition computation using action potential timing for stimulus representation publication-title: Nature doi: 10.1038/376033a0 – volume: 5 start-page: 157 issue: 2 year: 1994 ident: 10.1016/j.neunet.2018.12.002_b14 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.279181 – volume: 35 start-page: 2706 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b177 article-title: Mapping from frame-driven to frame-free event-driven vision systems by low-rate rate-coding and coincidence processing. application to feed forward convnets publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2013.71 – volume: 118 issue: 13 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b232 article-title: Emergence of compositional representations in restricted Boltzmann machines publication-title: Physical Review Letters doi: 10.1103/PhysRevLett.118.138301 – volume: 86 start-page: 1033 issue: 3 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b35 article-title: Spike timing-dependent plasticity: From synapse to perception publication-title: Physiological Reviews doi: 10.1152/physrev.00030.2005 – volume: 33 start-page: 42 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b29 article-title: Advancing interconnect density for spiking neural network hardware implementations using traffic-aware adaptive network-on-chip routers publication-title: Neural Networks doi: 10.1016/j.neunet.2012.04.004 – start-page: 473 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b197 article-title: Deep belief network for clustering and classification of a continuous data – start-page: 1 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b226 article-title: BP-STDP: Approximating Backpropagation using spike timing dependent plasticity publication-title: Neurocomputing – start-page: 1 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b202 article-title: A 45nm cmos neuromorphic chip with a scalable architecture for learning in networks of spiking neurons – volume: 3 start-page: 919 issue: 9 year: 2000 ident: 10.1016/j.neunet.2018.12.002_b208 article-title: Competitive Hebbian learning through spike-timing-dependent synaptic plasticity publication-title: Nature Neuroscience doi: 10.1038/78829 – volume: 427 start-page: 244 issue: 6971 year: 2004 ident: 10.1016/j.neunet.2018.12.002_b104 article-title: Bayesian integration in sensorimotor learning publication-title: Nature doi: 10.1038/nature02169 – volume: 10 issue: 3 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b90 article-title: STDP installs in winner-take-all circuits an online approximation to hidden Markov model learning publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1003511 – ident: 10.1016/j.neunet.2018.12.002_b169 – volume: 160 start-page: 106 issue: 1 year: 1962 ident: 10.1016/j.neunet.2018.12.002_b80 article-title: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex publication-title: The Journal of Physiology doi: 10.1113/jphysiol.1962.sp006837 – volume: 7 issue: 11 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b23 article-title: Neural dynamics as sampling: A model for stochastic computation in recurrent networks of spiking neurons publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1002211 – volume: 268 start-page: 1503 year: 1995 ident: 10.1016/j.neunet.2018.12.002_b136 article-title: Reliability of spike timing in neocortical neurons publication-title: Science doi: 10.1126/science.7770778 – volume: 26 start-page: 9673 issue: 38 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b179 article-title: Triplets of spikes in a model of spike timing-dependent plasticity publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.1425-06.2006 – ident: 10.1016/j.neunet.2018.12.002_b32 – year: 2016 ident: 10.1016/j.neunet.2018.12.002_b61 – volume: 10 start-page: 92 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b99 article-title: Humans and deep networks largely agree on which kinds of variation make object recognition harder publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2016.00092 – volume: 8 start-page: 1 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b161 article-title: Event-driven contrastive divergence for spiking neuromorphic systems publication-title: Frontiers in Neuroscience – volume: 12 start-page: 1 issue: 774 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b178 article-title: Deep learning with spiking neurons: Opportunities and challenges publication-title: Frontiers in Neuroscience – volume: 99 start-page: 56 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b98 article-title: STDP-based spiking deep convolutional neural networks for object recognition publication-title: Neural Networks doi: 10.1016/j.neunet.2017.12.005 – volume: 19 start-page: 2881 issue: 11 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b21 article-title: Learning real-world stimuli in a neural network with spike-driven synaptic dynamics publication-title: Neural Computation doi: 10.1162/neco.2007.19.11.2881 – volume: 1 start-page: 1 issue: 1 year: 1991 ident: 10.1016/j.neunet.2018.12.002_b49 article-title: Distributed hierarchical processing in the primate cerebral cortex publication-title: Cerebral Cortex doi: 10.1093/cercor/1.1.1 – start-page: 2352 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b186 article-title: Deep convolutional neural networks for image classification: A comprehensive review publication-title: Neural Computation doi: 10.1162/neco_a_00990 – volume: 14 start-page: 2531 issue: 11 year: 2002 ident: 10.1016/j.neunet.2018.12.002_b135 article-title: Real-time computing without stable states: A new framework for neural computation based on perturbations publication-title: Neural Computation doi: 10.1162/089976602760407955 – volume: 8 start-page: 8912 issue: 1 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b42 article-title: Modelling peri-perceptual brain processes in a deep learning spiking neural network architecture publication-title: Scientific Reports doi: 10.1038/s41598-018-27169-8 – volume: 20 start-page: 1631 issue: 6 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b113 article-title: Representational power of restricted boltzmann machines and deep belief networks publication-title: Neural Computation doi: 10.1162/neco.2008.04-07-510 – volume: 79 start-page: 633 issue: 3 year: 1990 ident: 10.1016/j.neunet.2018.12.002_b30 article-title: A decrease in firing threshold observed after induction of the EPSP-spike (ES) component of long-term potentiation in rat hippocampal slices publication-title: Experimental Brain Research doi: 10.1007/BF00229331 – volume: 345 start-page: 668 issue: 6197 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b147 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science doi: 10.1126/science.1254642 – start-page: 1609 year: 2004 ident: 10.1016/j.neunet.2018.12.002_b244 article-title: Probabilistic computation in spiking populations – volume: 8 start-page: 1 issue: 1 year: 1996 ident: 10.1016/j.neunet.2018.12.002_b132 article-title: Lower bounds for the computational power of networks of spiking neurons publication-title: Neural Computation doi: 10.1162/neco.1996.8.1.1 – ident: 10.1016/j.neunet.2018.12.002_b201 – start-page: 1357 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b167 article-title: STDP enables spiking neurons to detect hidden causes of their inputs – volume: 3 issue: 1 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b140 article-title: Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains publication-title: PloS One doi: 10.1371/journal.pone.0001377 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.neunet.2018.12.002_b74 article-title: Long short-term memory publication-title: Neural Computation doi: 10.1162/neco.1997.9.8.1735 – ident: 10.1016/j.neunet.2018.12.002_b125 doi: 10.1109/CVPR.2014.233 – year: 2015 ident: 10.1016/j.neunet.2018.12.002_b84 article-title: Neuromorphic architectures for spiking deep neural networks – volume: 6 issue: 4 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b198 article-title: Independent component analysis in spiking neurons publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.1000757 – year: 2018 ident: 10.1016/j.neunet.2018.12.002_b211 – volume: 82 start-page: 284 issue: 3 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b46 article-title: Action recognition using a bio-inspired feedforward spiking network publication-title: International Journal of Computer Vision doi: 10.1007/s11263-008-0201-1 – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b221 article-title: Studying the interaction of a hidden Markov model with a Bayesian spiking neural network – volume: 8 start-page: 1185 issue: 6 year: 1996 ident: 10.1016/j.neunet.2018.12.002_b5 article-title: Temporal precision of spike trains in extrastriate cortex of the behaving macaque monkey publication-title: Neural Computation doi: 10.1162/neco.1996.8.6.1185 – volume: 31 start-page: 15844 issue: 44 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b69 article-title: Natural movies evoke spike trains with low spike time variability in cat primary visual cortex publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.5153-10.2011 – volume: 10 start-page: 508 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b119 article-title: Training deep spiking neural networks using backpropagation publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2016.00508 – volume: 21 start-page: 1259 issue: 5 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b141 article-title: Competitive STDP-based spike pattern learning publication-title: Neural computation doi: 10.1162/neco.2008.06-08-804 – volume: 381 start-page: 607 issue: 6583 year: 1996 ident: 10.1016/j.neunet.2018.12.002_b170 article-title: Emergence of simple-cell receptive field properties by learning a sparse code for natural images publication-title: Nature doi: 10.1038/381607a0 – start-page: 3366 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b1 article-title: Exploring convolutional neural network structures and optimization techniques for speech recognition – ident: 10.1016/j.neunet.2018.12.002_b164 – start-page: 8614 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b196 article-title: Deep convolutional neural networks for LVCSR – volume: 219 start-page: 197 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b209 article-title: Asynchronous spiking neural P systems with local synchronization publication-title: Information Sciences doi: 10.1016/j.ins.2012.07.023 – volume: 95 start-page: 245 issue: 2 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b67 article-title: Neuroscience-inspired artificial intelligence publication-title: Neuron doi: 10.1016/j.neuron.2017.06.011 – volume: 14 start-page: 1569 issue: 6 year: 2003 ident: 10.1016/j.neunet.2018.12.002_b85 article-title: Simple model of spiking neurons publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2003.820440 – volume: 22 start-page: 2192 issue: 8 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b114 article-title: Deep belief networks are compact universal approximators publication-title: Neural Computation doi: 10.1162/neco.2010.08-09-1081 – volume: 24 start-page: 2451 issue: 12 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b28 article-title: Scalable hierarchical network-on-chip architecture for spiking neural network hardware implementations publication-title: IEEE Transactions on Parallel and Distributed Systems doi: 10.1109/TPDS.2012.289 – start-page: 1 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b53 article-title: Variability-tolerant convolutional neural network for pattern recognition applications based on oxram synapses – start-page: 234 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b91 article-title: Evolving spiking neural networks and neurogenetic systems for spatio-and spectro-temporal data modelling and pattern recognition – volume: 10 start-page: 1659 issue: 9 year: 1997 ident: 10.1016/j.neunet.2018.12.002_b133 article-title: Networks of spiking neurons: The third generation of neural network models publication-title: Neural networks doi: 10.1016/S0893-6080(97)00011-7 – volume: 33 start-page: 5475 issue: 13 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b101 article-title: Inhibitory interneurons decorrelate excitatory cells to drive sparse code formation in a spiking model of V1 publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.4188-12.2013 – volume: 22 issue: 04 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b152 article-title: Span: Spike pattern association neuron for learning spatio-temporal spike patterns publication-title: International Journal of Neural Systems doi: 10.1142/S0129065712500128 – volume: 319 start-page: 1108 issue: 5866 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b60 article-title: Rapid neural coding in the retina with relative spike latencies publication-title: Science doi: 10.1126/science.1149639 – volume: 12 start-page: 1 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b231 article-title: Event-based, timescale invariant unsupervised online learning with STDP publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2018.00046 – ident: 10.1016/j.neunet.2018.12.002_b142 – volume: 12 start-page: 42 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b175 article-title: A retinotopic spiking neural network system for accurate recognition of moving objects using NeuCube and dynamic vision sensors publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2018.00042 – volume: 16 start-page: 101 issue: 1 year: 2006 ident: 10.1016/j.neunet.2018.12.002_b96 article-title: Comparison of supervised learning platforms for spike time coding in spiking neural networks publication-title: International Journal of Applied Mathematics and Computer Science – start-page: 1422 year: 2011 ident: 10.1016/j.neunet.2018.12.002_b22 article-title: Sequence learning with hidden units in spiking neural networks – start-page: 1 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b105 – volume: 13 start-page: 1445 issue: 5 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b137 article-title: Applications of deep learning in biomedicine publication-title: Molecular Pharmaceutics doi: 10.1021/acs.molpharmaceut.5b00982 – start-page: 248 year: 2009 ident: 10.1016/j.neunet.2018.12.002_b38 article-title: Imagenet: A large-scale hierarchical image database – volume: 338 start-page: 1202 issue: 6111 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b44 article-title: A large-scale model of the functioning brain publication-title: Science doi: 10.1126/science.1225266 – volume: 9 start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b39 article-title: Unsupervised learning of digit recognition using spike-timing-dependent plasticity publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2015.00099 – volume: 205 start-page: 382 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b97 article-title: Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.04.029 – volume: 90 start-page: 211 issue: 2 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b227 article-title: Training a hidden Markov model with a Bayesian spiking neural network publication-title: Journal of Signal Processing Systems doi: 10.1007/s11265-016-1153-2 – volume: 105 start-page: 294 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b230 article-title: Representation learning using event-based STDP publication-title: Neural Networks doi: 10.1016/j.neunet.2018.05.018 – volume: 12 start-page: 288 issue: 3 year: 2013 ident: 10.1016/j.neunet.2018.12.002_b184 article-title: Immunity to device variations in a spiking neural network with memristive nanodevices publication-title: IEEE Transactions on Nanotechnology doi: 10.1109/TNANO.2013.2250995 – volume: Vol. 4 start-page: 2076 year: 2005 ident: 10.1016/j.neunet.2018.12.002_b128 article-title: Exploration of rank order coding with spiking neural networks for speech recognition – volume: 3 issue: 2 year: 2007 ident: 10.1016/j.neunet.2018.12.002_b143 article-title: Unsupervised learning of visual features through spike timing dependent plasticity publication-title: PLoS Computational Biology doi: 10.1371/journal.pcbi.0030031 – volume: 71 start-page: 2563 issue: 13 year: 2008 ident: 10.1016/j.neunet.2018.12.002_b241 article-title: Fast and adaptive network of spiking neurons for multi-view visual pattern recognition publication-title: Neurocomputing doi: 10.1016/j.neucom.2007.12.038 – year: 2018 ident: 10.1016/j.neunet.2018.12.002_b93 – volume: Vol. 10 start-page: 339 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b66 article-title: Learning features from music audio with deep belief networks – volume: 168 start-page: 413 issue: 3 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b207 article-title: Cellular and circuit mechanisms shaping the perceptual properties of the primate fovea publication-title: Cell doi: 10.1016/j.cell.2017.01.005 – year: 2002 ident: 10.1016/j.neunet.2018.12.002_b185 – volume: 34 start-page: 1 year: 2012 ident: 10.1016/j.neunet.2018.12.002_b6 article-title: On the equivalence of Hopfield networks and Boltzmann machines publication-title: Neural Networks doi: 10.1016/j.neunet.2012.06.003 – volume: 11 start-page: 324 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b160 article-title: Event-driven random back-propagation: Enabling neuromorphic deep learning machines publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2017.00324 – volume: 11 start-page: 682 year: 2017 ident: 10.1016/j.neunet.2018.12.002_b193 article-title: Conversion of continuous-valued deep networks to efficient event-driven networks for image classification publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2017.00682 – volume: 12 issue: 12 year: 2014 ident: 10.1016/j.neunet.2018.12.002_b218 article-title: Millisecond-scale motor encoding in a cortical vocal area publication-title: PLoS Biology doi: 10.1371/journal.pbio.1002018 – volume: 5 year: 2015 ident: 10.1016/j.neunet.2018.12.002_b86 article-title: Improving protein fold recognition by deep learning networks publication-title: Scientific Reports doi: 10.1038/srep17573 – start-page: 293 year: 2016 ident: 10.1016/j.neunet.2018.12.002_b165 article-title: Learning to be efficient: Algorithms for training low-latency, low-compute deep spiking neural networks – volume: 97 issue: 2 year: 2018 ident: 10.1016/j.neunet.2018.12.002_b8 article-title: Phase diagram of restricted Boltzmann machines and generalized Hopfield networks with arbitrary priors publication-title: Physical Review E doi: 10.1103/PhysRevE.97.022310 – start-page: ENEURO year: 2016 ident: 10.1016/j.neunet.2018.12.002_b176 article-title: Learning probabilistic inference through STDP publication-title: eneuro – volume: 21 start-page: 1817 issue: 11 year: 2010 ident: 10.1016/j.neunet.2018.12.002_b238 article-title: SWAT: A spiking neural network training algorithm for classification problems publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2010.2074212 – start-page: 87 year: 2001 ident: 10.1016/j.neunet.2018.12.002_b75 article-title: Learning to learn using gradient descent |
| SSID | ssj0006843 |
| Score | 2.6993084 |
| SecondaryResourceType | review_article |
| Snippet | In recent years, deep learning has revolutionized the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer)... |
| SourceID | hal proquest pubmed crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 47 |
| SubjectTerms | Action Potentials - physiology Algorithms Biological plausibility Brain - physiology Computer Science Deep learning Deep Learning - trends Humans Machine Learning Machine Learning - trends Models, Neurological Neural and Evolutionary Computing Neural Networks (Computer) Neurons - physiology Power-efficient architecture Spiking neural network |
| Title | Deep learning in spiking neural networks |
| URI | https://dx.doi.org/10.1016/j.neunet.2018.12.002 https://www.ncbi.nlm.nih.gov/pubmed/30682710 https://www.proquest.com/docview/2179416239 https://hal.science/hal-02341924 |
| Volume | 111 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8QgEJ74uHjx_VhfqcaDF9y2UFqOGx9Znxc18UbKFnSNqRt316O_3ZmWrjHRmHgsAUqGYeYDPmYADlQY256VOYuddEzwNGXGpQnL8zQrOM9j6eg18vWN7N6Li4fkYQqOm7cwRKv0tr-26ZW19iVtL832oN9v34boaiUCHlTKkHNOdliIlLT86OOL5iGzmjmHlRnVbp7PVRyv0o5LS4zKKKsOBf3hyg_uafqJeJK_gdDKGZ0twrxHkUGnHugSTNlyGRaaDA2BX7ArcHhi7SDwmSEeg34ZDAd9OhwPKI4l9lDWLPDhKtyfnd4dd5nPjcB6QqgRU8LY0HCHACvnmROmMEWMmycijwmFnk9lOQUepLznRliZGJvYIskjFFmqcGe6BjPla2k3IMAtSxGHqUyKnhOFzVSkEqeclcKZIhSmBbwRie75wOGUv-JFNwyxZ10LUpMgdRRrFGQL2KTVoA6c8Uf9tJG2_qYAGm37Hy33cXImP6F42d3OlaYyBCR0yy3eoxbsNXOncQHRrUhe2tfxUMdkkiJEgaoF6_WkTvrC_VQWIwbb_PfgtmAOv1TNWtuGmdHb2O4gjBmZ3UpPd2G2c37ZvfkEdJPvmA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT-MwEB5Be1gusMtrA_sIqz1wsZrEjhMfK9gqXUovCxI3K25sKFqlFW339-9M41RCAiFxdWzHGtsz39ifZwB-qiixEytLljjpmOBZxozLUlaWWV5xXibS0Wvk67EsbsXvu_RuCy7atzBEq_S6v9Hpa23tS3pemr35dNr7E6GplQh4cFFGnHPUw12KTpV2oNsfXhXjjUKWeUOew_qMGrQv6NY0r9quakukyjhfnwv685UXLNT2A1ElX8Oha3s0-Ai7HkiG_Wasn2DL1vuw1yZpCP2ePYDzS2vnoU8OcR9O63Axn9L5eEihLLGHuiGCLw7hdvDr5qJgPj0CmwihlkwJYyPDHWKskudOmMpUCfpPxB8TCo2fykuKPUipz42wMjU2tVVaxii1TKFzegSdelbbzxCi11IlUSbTauJEZXMVq9QpZ6VwpoqECYC3ItETHzucUlj81S1J7FE3gtQkSB0nGgUZANu0mjexM96on7XS1s_WgEb1_kbLHzg5m59QyOyiP9JUhpiELrrFvziAs3buNO4huhgpaztbLXRCWilGIKgCOG4mddMXulR5gjDs5N2D-w4fipvrkR4Nx1ensINfVENi-wKd5dPKfkVUszTf_Kr9D7MZ8kk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+in+spiking+neural+networks&rft.jtitle=Neural+networks&rft.au=Tavanaei%2C+Amirhossein&rft.au=Ghodrati%2C+Masoud&rft.au=Kheradpisheh%2C+Saeed+Reza&rft.au=Masquelier%2C+Timoth%C3%A9e&rft.date=2019-03-01&rft.issn=0893-6080&rft.volume=111&rft.spage=47&rft.epage=63&rft_id=info:doi/10.1016%2Fj.neunet.2018.12.002&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neunet_2018_12_002 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |