Efficient in situ learning of hybrid LIF neurons using WTA mechanism for high-speed low-power neuromorphic systems
Abstract The emerging market for hardware neuromorphic systems has fulfilled the growing demand for fast and energy-efficient computer architectures. Memristor-based neural networks are a viable approach to meet the need for low-power neuromorphic devices. Spiking neural networks (SNNs) are widely r...
Saved in:
Published in | Physica scripta Vol. 99; no. 10; pp. 106010 - 106025 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
IOP Publishing
01.10.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Abstract The emerging market for hardware neuromorphic systems has fulfilled the growing demand for fast and energy-efficient computer architectures. Memristor-based neural networks are a viable approach to meet the need for low-power neuromorphic devices. Spiking neural networks (SNNs) are widely recognized as the best hardware solution for mimicking the brain’s efficient processing capabilities. To build the SNN model, we have designed an energy-efficient hybrid Leaky Integrated and Fire (LIF) neuron model using Carbon Nano Tube Field Effect Transistors (CNTFET) and memristors. This hybrid neuron operates at 3.89 MHz, with 1.047nW and 0.257fJ of power and energy per spike with a constant power supply (V dd ) and an excitation voltage of 0.5V, under the ideal conditions. When the intrinsic constraints of CNTFETs and memristors, such as parasitic elements and hysteresis effects, are taken into consideration, the operating frequency is lowered to 3.45 MHz (an 11.5% decrease), and energy consumption rises to 0.317 fJ per spike (a 23.3% increase). Despite these limitations, our design outperforms with existing works. On the other hand the development of in situ , Spike Timing Dependent Plasticity (STDP) learning through memristors as synapses results in a computational challenge. In this paper, we adopt a potent technique capable of carrying out both learning and inference. The weight modulation is accomplished using a linear memristor model, resulting in high speed and reduced power consumption. We intend to apply the winner-takes-all (WTA) mechanism within the SNN architecture, which incorporates recurrently connected proposed neurons in the output layer, for real-time pattern recognition. The proposed design has been implemented and the performance metrics superseded the existing works in terms of power, energy, and accuracy. Furthermore, the design is capable of classifying 50×10 4 images per second. |
---|---|
AbstractList | Abstract The emerging market for hardware neuromorphic systems has fulfilled the growing demand for fast and energy-efficient computer architectures. Memristor-based neural networks are a viable approach to meet the need for low-power neuromorphic devices. Spiking neural networks (SNNs) are widely recognized as the best hardware solution for mimicking the brain’s efficient processing capabilities. To build the SNN model, we have designed an energy-efficient hybrid Leaky Integrated and Fire (LIF) neuron model using Carbon Nano Tube Field Effect Transistors (CNTFET) and memristors. This hybrid neuron operates at 3.89 MHz, with 1.047nW and 0.257fJ of power and energy per spike with a constant power supply (V dd ) and an excitation voltage of 0.5V, under the ideal conditions. When the intrinsic constraints of CNTFETs and memristors, such as parasitic elements and hysteresis effects, are taken into consideration, the operating frequency is lowered to 3.45 MHz (an 11.5% decrease), and energy consumption rises to 0.317 fJ per spike (a 23.3% increase). Despite these limitations, our design outperforms with existing works. On the other hand the development of in situ , Spike Timing Dependent Plasticity (STDP) learning through memristors as synapses results in a computational challenge. In this paper, we adopt a potent technique capable of carrying out both learning and inference. The weight modulation is accomplished using a linear memristor model, resulting in high speed and reduced power consumption. We intend to apply the winner-takes-all (WTA) mechanism within the SNN architecture, which incorporates recurrently connected proposed neurons in the output layer, for real-time pattern recognition. The proposed design has been implemented and the performance metrics superseded the existing works in terms of power, energy, and accuracy. Furthermore, the design is capable of classifying 50×10 4 images per second. |
Author | Hussain, Syed Ali Sanki, Pradyut Kumar Prasad V, P N S B S V |
Author_xml | – sequence: 1 givenname: Syed Ali orcidid: 0000-0002-9513-9712 surname: Hussain fullname: Hussain, Syed Ali organization: SRM University -AP , Department of Electronics and Communication Engineering, Neerukonda, 522240, India – sequence: 2 givenname: P N S B S V orcidid: 0000-0003-2424-6948 surname: Prasad V fullname: Prasad V, P N S B S V organization: SRM University -AP , Department of Electronics and Communication Engineering, Neerukonda, 522240, India – sequence: 3 givenname: Pradyut Kumar orcidid: 0000-0002-1625-1512 surname: Sanki fullname: Sanki, Pradyut Kumar organization: SRM University -AP , Department of Electronics and Communication Engineering, Neerukonda, 522240, India |
BookMark | eNp1kEFrwjAUx8NwMHW775gPsM60SdPkKKKbIOwi7Fhi8mIjNimJRfz2s3TsttOD997vz5_fDE188IDQa07ecyLEImekyJiQfKFMJXX5gKZ_qwmaEkLzTEgmn9AspRMhBS-4nKK4ttZpB_6CncfJXXp8BhW980ccLG5uh-gM3m032EMfg0-4T8Pte7_ELehGeZdabEPEjTs2WeoADD6Ha9aFK8QRakPsGqdxuqULtOkZPVp1TvDyO-dov1nvV5_Z7utju1ruMl2JMrMlV4xWpQGjjeSUmgOnBQFFCw4ATOdFSU3FJBeU20LkllGirJXacsbLis4RGWN1DClFsHUXXavirc5JPSirBz_14Kceld2RtxFxoatPoY_-3u__9x-r_HCR |
CODEN | PHSTBO |
Cites_doi | 10.1007/s11664-024-11078-w 10.1109/TIE.2014.2356439 10.1016/j.mejo.2014.12.006 10.1038/nnano.2016.70 10.1088/1674-4926/36/3/034001 10.1016/j.nanoen.2022.108091 10.1007/s13369-022-07290-7 10.1109/TCSII.2020.2980054 10.1109/TNANO.2018.2821131 10.1007/BF03353650 10.1149/MA2020-02312058mtgabs 10.1038/s41928-017-0006-8 10.1016/j.neucom.2019.06.048 10.1109/TCAD.2013.2252057 10.1109/TVLSI.2021.3069221 10.1109/JETCAS.2015.2433552 10.3390/electronics13030605 10.1063/1.5120973 10.1109/TVLSI.2018.2815025 10.1038/ncomms3072 10.3389/fncom.2015.00099 10.1109/LED.2018.2805822 10.1109/TNNLS.2020.2995631 10.2417/1201011.003396 10.1002/pssr.202000389 10.1109/TETCI.2018.2829914 10.1109/TCAD.2016.2578881 10.1038/s41598-018-27033-9 10.1007/s10825-019-01357-9 10.1016/j.neunet.2023.06.019 10.3390/electronics10050530 10.1016/j.neunet.2007.12.037 |
ContentType | Journal Article |
Copyright | 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved. |
Copyright_xml | – notice: 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved. |
DBID | AAYXX CITATION |
DOI | 10.1088/1402-4896/ad79c5 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 1402-4896 |
ExternalDocumentID | 10_1088_1402_4896_ad79c5 psad79c5 |
GroupedDBID | -~X 123 1JI 4.4 5B3 5PX 5VS 7.M 7.Q AAGCD AAGID AAJIO AAJKP AATNI ABCXL ABJNI ABLJU ABQJV ABVAM ACAFW ACGFS ACHIP AEFHF AENEX AFYNE AKPSB ALMA_UNASSIGNED_HOLDINGS AOAED ASPBG ATQHT AVWKF AZFZN CBCFC CEBXE CJUJL CRLBU CS3 DU5 EBS EDWGO EMSAF EPQRW EQZZN IJHAN IOP IZVLO KOT LAP MV1 N5L N9A PJBAE RIN RNS ROL RPA SJN SY9 TN5 W28 WH7 XPP ~02 AAYXX CITATION |
ID | FETCH-LOGICAL-c785-f56a4375dedcd9633db6320ea326eee4c1253d7496836f281f430aff9cf646573 |
IEDL.DBID | IOP |
ISSN | 0031-8949 |
IngestDate | Wed Sep 25 14:10:58 EDT 2024 Tue Oct 01 22:12:01 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 10 |
Language | English |
License | This article is available under the terms of the IOP-Standard License. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c785-f56a4375dedcd9633db6320ea326eee4c1253d7496836f281f430aff9cf646573 |
Notes | PHYSSCR-132323.R2 |
ORCID | 0000-0002-1625-1512 0000-0003-2424-6948 0000-0002-9513-9712 |
PageCount | 16 |
ParticipantIDs | iop_journals_10_1088_1402_4896_ad79c5 crossref_primary_10_1088_1402_4896_ad79c5 |
PublicationCentury | 2000 |
PublicationDate | 2024-10-01 |
PublicationDateYYYYMMDD | 2024-10-01 |
PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-01 day: 01 |
PublicationDecade | 2020 |
PublicationTitle | Physica scripta |
PublicationTitleAbbrev | PS |
PublicationTitleAlternate | Phys. Scr |
PublicationYear | 2024 |
Publisher | IOP Publishing |
Publisher_xml | – name: IOP Publishing |
References | Velichko (psad79c5bib2) 2019 Tang (psad79c5bib34) 2023 Rziga (psad79c5bib30) 2019; 18 Moaiyeri (psad79c5bib33) 2011; 3 Elhamdaoui (psad79c5bib32) 2020 Shinde (psad79c5bib24) 2015; 36 Zheng (psad79c5bib19) 2018; 17 Cho (psad79c5bib27) 2015; 46 Yakopcic (psad79c5bib29) 2013; 32 Chen (psad79c5bib38) 2021; 29 Vohra (psad79c5bib40) 2022 Wu (psad79c5bib41) 2015; 5 Zhao (psad79c5bib13) 2020; 67 Chen (psad79c5bib12) 2024; 13 Shamsi (psad79c5bib37) 2018; 26 Elhamdaoui (psad79c5bib20) 2023; 48 Wang (psad79c5bib21) 2019; 115 Yan (psad79c5bib8) 2023; 107 Alibart (psad79c5bib14) 2013; 4 Wijekoon (psad79c5bib3) 2008; 21 Hansen (psad79c5bib18) 2018; 8 Laiho (psad79c5bib25) 2010 Huynh (psad79c5bib1) 2022 Zidan (psad79c5bib23) 2018; 1 Shi (psad79c5bib10) 2018; 2 Wang (psad79c5bib22) 2019; 125 Saxena (psad79c5bib42) 2018 Hussain (psad79c5bib7) 2024 Chen (psad79c5bib26) 2016; 36 Chu (psad79c5bib39) 2014; 62 Pechmann (psad79c5bib35) 2021; 10 Kim (psad79c5bib31) 2020; 31 Yang (psad79c5bib43) 2019; 363 Lashkare (psad79c5bib5) 2018; 39 Dong (psad79c5bib16) 2023; 165 Xiao (psad79c5bib11) 2020; 32 Gao (psad79c5bib9) 2020; 14 Biolek (psad79c5bib28) 2009; 18 Merolla (psad79c5bib4) 2011 Yakopcic (psad79c5bib15) 2015 Lynch (psad79c5bib36) 2019 Tuma (psad79c5bib6) 2016; 11 Diehl (psad79c5bib17) 2015; 9 |
References_xml | – start-page: 1 year: 2024 ident: psad79c5bib7 article-title: Leaky integrate-and-fire neuron model-based snn latency estimation using fns publication-title: J. Electron. Mater. doi: 10.1007/s11664-024-11078-w contributor: fullname: Hussain – volume: 62 start-page: 2410 year: 2014 ident: psad79c5bib39 article-title: Neuromorphic hardware system for visual pattern recognition with memristor array and cmos neuron publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2014.2356439 contributor: fullname: Chu – start-page: 1 year: 2015 ident: psad79c5bib15 article-title: Memristor based neuromorphic circuit for ex-situ training of multi-layer neural network algorithms contributor: fullname: Yakopcic – volume: 46 start-page: 214 year: 2015 ident: psad79c5bib27 article-title: Memristor-cmos logic and digital computational components publication-title: Microelectron. J. doi: 10.1016/j.mejo.2014.12.006 contributor: fullname: Cho – volume: 11 start-page: 693 year: 2016 ident: psad79c5bib6 article-title: Stochastic phase-change neurons publication-title: Nat. Nanotechnol. doi: 10.1038/nnano.2016.70 contributor: fullname: Tuma – volume: 125 year: 2019 ident: psad79c5bib22 article-title: ϕmemristor: real memristor found publication-title: J. Appl. Phys. contributor: fullname: Wang – volume: 36 year: 2015 ident: psad79c5bib24 article-title: Modelling of nanostructured tio2-based memristors publication-title: J. Semicond. doi: 10.1088/1674-4926/36/3/034001 contributor: fullname: Shinde – volume: 107 year: 2023 ident: psad79c5bib8 article-title: A low-power si: Hfo2 ferroelectric tunnel memristor for spiking neural networks publication-title: Nano Energy doi: 10.1016/j.nanoen.2022.108091 contributor: fullname: Yan – year: 2022 ident: psad79c5bib1 article-title: Implementing spiking neural networks on neuromorphic architectures: A review contributor: fullname: Huynh – volume: 48 start-page: 6175 year: 2023 ident: psad79c5bib20 article-title: The egm model and the winner-takes-all (wta) mechanism for a memristor-based neural network publication-title: Arab. J. Sci. Eng. doi: 10.1007/s13369-022-07290-7 contributor: fullname: Elhamdaoui – volume: 67 start-page: 931 year: 2020 ident: psad79c5bib13 article-title: A memristor-based spiking neural network with high scalability and learning efficiency publication-title: IEEE Trans. Circuits Syst. Express Briefs doi: 10.1109/TCSII.2020.2980054 contributor: fullname: Zhao – volume: 17 start-page: 520 year: 2018 ident: psad79c5bib19 article-title: Learning in memristor crossbar-based spiking neural networks through modulation of weight-dependent spike-timing-dependent plasticity publication-title: IEEE Trans. Nanotechnol. doi: 10.1109/TNANO.2018.2821131 contributor: fullname: Zheng – volume: 3 start-page: 43 year: 2011 ident: psad79c5bib33 article-title: Efficient cntfet-based ternary full adder cells for nanoelectronics publication-title: Nano-Micro Letters doi: 10.1007/BF03353650 contributor: fullname: Moaiyeri – volume: 31 start-page: 2058 year: 2020 ident: psad79c5bib31 article-title: Cross-point synapse array fabricated with hfo2 based memristor-cells and super-linear threshold selectors and hfo2 based integrate-and-fire neurons doi: 10.1149/MA2020-02312058mtgabs contributor: fullname: Kim – volume: 18 year: 2009 ident: psad79c5bib28 article-title: Spice model of memristor with nonlinear dopant drift publication-title: Radioengineering contributor: fullname: Biolek – volume: 1 start-page: 22 year: 2018 ident: psad79c5bib23 article-title: The future of electronics based on memristive systems publication-title: Nature electronics doi: 10.1038/s41928-017-0006-8 contributor: fullname: Zidan – volume: 363 start-page: 114 year: 2019 ident: psad79c5bib43 article-title: A memristor-based neural network circuit with synchronous weight adjustment publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.06.048 contributor: fullname: Yang – volume: 32 start-page: 1201 year: 2013 ident: psad79c5bib29 article-title: Generalized memristive device spice model and its application in circuit design publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. doi: 10.1109/TCAD.2013.2252057 contributor: fullname: Yakopcic – volume: 29 start-page: 1095 year: 2021 ident: psad79c5bib38 article-title: Competitive neural network circuit based on winner-take-all mechanism and online hebbian learning rule publication-title: IEEE Trans. Very Large Scale Integr. VLSI Syst. doi: 10.1109/TVLSI.2021.3069221 contributor: fullname: Chen – year: 2022 ident: psad79c5bib40 article-title: Cmos circuit implementation of spiking neural network for pattern recognition using on-chip unsupervised stdp learning contributor: fullname: Vohra – volume: 5 start-page: 254 year: 2015 ident: psad79c5bib41 article-title: Homogeneous spiking neuromorphic system for real-world pattern recognition publication-title: IEEE Journal on Emerging and Selected Topics in Circuits and Systems doi: 10.1109/JETCAS.2015.2433552 contributor: fullname: Wu – volume: 13 start-page: 605 year: 2024 ident: psad79c5bib12 article-title: Full-custom 90 nm cntfet process design kit: characterization, modeling, and implementation publication-title: Electronics doi: 10.3390/electronics13030605 contributor: fullname: Chen – volume: 115 year: 2019 ident: psad79c5bib21 article-title: Winner-takes-all mechanism realized by memristive neural network publication-title: Appl. Phys. Lett. doi: 10.1063/1.5120973 contributor: fullname: Wang – volume: 26 start-page: 2795 year: 2018 ident: psad79c5bib37 article-title: A hardware architecture for columnar-organized memory based on cmos neuron and memristor crossbar arrays publication-title: IEEE Trans. Very Large Scale Integr. VLSI Syst. doi: 10.1109/TVLSI.2018.2815025 contributor: fullname: Shamsi – volume: 4 start-page: 2072 year: 2013 ident: psad79c5bib14 article-title: Pattern classification by memristive crossbar circuits using ex situ and in situ training publication-title: Nat. Commun. doi: 10.1038/ncomms3072 contributor: fullname: Alibart – volume: 9 start-page: 99 year: 2015 ident: psad79c5bib17 article-title: Unsupervised learning of digit recognition using spike-timing-dependent plasticity publication-title: Frontiers in computational neuroscience doi: 10.3389/fncom.2015.00099 contributor: fullname: Diehl – year: 2019 ident: psad79c5bib36 contributor: fullname: Lynch – volume: 39 start-page: 484 year: 2018 ident: psad79c5bib5 article-title: Pcmo rram for integrate-and-fire neuron in spiking neural networks publication-title: IEEE Electron Device Lett. doi: 10.1109/LED.2018.2805822 contributor: fullname: Lashkare – volume: 32 start-page: 1974 year: 2020 ident: psad79c5bib11 article-title: Qualitative analysis and bifurcation in a neuron system with memristor characteristics and time delay publication-title: IEEE Trans Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2020.2995631 contributor: fullname: Xiao – start-page: 1 year: 2010 ident: psad79c5bib25 article-title: Memristive synapses are becoming reality publication-title: The Neuromorphic Engineer doi: 10.2417/1201011.003396 contributor: fullname: Laiho – volume: 14 year: 2020 ident: psad79c5bib9 article-title: A high-performance memristor device and its filter circuit application publication-title: physica status solidi (RRL)–Rapid Research Letters doi: 10.1002/pssr.202000389 contributor: fullname: Gao – volume: 2 start-page: 359 year: 2018 ident: psad79c5bib10 article-title: Memristor-based circuit design for neuron with homeostatic plasticity publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence doi: 10.1109/TETCI.2018.2829914 contributor: fullname: Shi – start-page: 1 year: 2018 ident: psad79c5bib42 article-title: Energy-efficient cmos memristive synapses for mixed-signal neuromorphic system-on-a-chip contributor: fullname: Saxena – volume: 36 start-page: 279 year: 2016 ident: psad79c5bib26 article-title: A logic circuit design for perfecting memristor-based material implication publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. doi: 10.1109/TCAD.2016.2578881 contributor: fullname: Chen – start-page: 1 year: 2020 ident: psad79c5bib32 article-title: Synapse design based on memristor contributor: fullname: Elhamdaoui – start-page: 1 year: 2011 ident: psad79c5bib4 article-title: A digital neurosynaptic core using embedded crossbar memory with 45pj per spike in 45nm contributor: fullname: Merolla – volume: 8 start-page: 8914 year: 2018 ident: psad79c5bib18 article-title: Unsupervised hebbian learning experimentally realized with analogue memristive crossbar arrays publication-title: Sci. Rep. doi: 10.1038/s41598-018-27033-9 contributor: fullname: Hansen – volume: 18 start-page: 1055 year: 2019 ident: psad79c5bib30 article-title: An efficient verilog-a memristor model implementation: simulation and application publication-title: J. Comput. Electron. doi: 10.1007/s10825-019-01357-9 contributor: fullname: Rziga – year: 2019 ident: psad79c5bib2 article-title: Oscillator circuit for spike neural network with sigmoid like activation function and firing rate coding contributor: fullname: Velichko – volume: 165 start-page: 799 year: 2023 ident: psad79c5bib16 article-title: An unsupervised stdp-based spiking neural network inspired by biologically plausible learning rules and connections publication-title: Neural Netw. doi: 10.1016/j.neunet.2023.06.019 contributor: fullname: Dong – start-page: 20 year: 2023 ident: psad79c5bib34 article-title: Constraints-aware training (cat) to enable software-hardware co-design for memristor-based analog neuromorphic chip contributor: fullname: Tang – volume: 10 start-page: 530 year: 2021 ident: psad79c5bib35 article-title: A versatile, voltage-pulse based read and programming circuit for multi-level rram cells publication-title: Electronics doi: 10.3390/electronics10050530 contributor: fullname: Pechmann – volume: 21 start-page: 524 year: 2008 ident: psad79c5bib3 article-title: Compact silicon neuron circuit with spiking and bursting behaviour publication-title: Neural Netw. doi: 10.1016/j.neunet.2007.12.037 contributor: fullname: Wijekoon |
SSID | ssj0026269 |
Score | 2.428045 |
Snippet | Abstract The emerging market for hardware neuromorphic systems has fulfilled the growing demand for fast and energy-efficient computer architectures.... |
SourceID | crossref iop |
SourceType | Aggregation Database Publisher |
StartPage | 106010 |
SubjectTerms | CNTFET LIF Neuron Memristor Patterns recognition SNN WTA |
Title | Efficient in situ learning of hybrid LIF neurons using WTA mechanism for high-speed low-power neuromorphic systems |
URI | https://iopscience.iop.org/article/10.1088/1402-4896/ad79c5 |
Volume | 99 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8QwEA66InjxLb7JQQ8esm6bNE3wtIjLrvg6rOhBKG2arEW3LbaL6K932lRRURBvLUzb8E3b-YbMfIPQXiyBJYeOQzSXESQonBLBhSFaaGlUxCWrxXTOL3j_mp3eerdT6OijFybLm19_Gw6tULCFsCmIE4eQEriECckPw9iXyptGMxB1O9XchsHl1Ue2BWuw3Jc6REgmmz3Kn-7wJSZNw3M_hZjeArp7X5ytLHloT8qorV6_6Tb-c_WLaL6hnrhrTZfQlE6X0WxdAqqKFfR0UqtJQBDCSYqLpJzgZqTECGcG379UvV34bNDDtQZmWuCqZn6Eb4ZdPNZVA3FSjDFwYFxJIJMih7iIH7NnkleD2OxF4wzcmihs9aOLVTTsnQyP-6SZyECULzxiPB4y6nuxjhU4mdI44tTt6BA4oNaaKWBLNPaZ5IJy4wrHMNoJjZHKcMY9n66hVpqleh1ho32lYqZcHjksFD7QkgjOpZI6BJziDXTw7pIgt7obQb1fLkRQQRhUEAYWwg20D2gHzcdX_Gq3-Ue7LTTnAnWxJXvbqFU-TfQOUI8y2q1fsTc7aNJA |
link.rule.ids | 315,786,790,27957,27958,38900,53877 |
linkProvider | IOP Publishing |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT4QwEG58ROPFt_FtD3rw0N2FltIejbpxfR_W6A2hD93oApHdGP31DhSNGk1MvEFSoHxDmW_SmW8Q2tYSWHLsecRwmUCAwikRXFhihJFWJVyySkzn7JwfXbHjm-Cm7nNa1cJkef3rb8ChEwp2ENYJcaIJIYFPmJC8GetQqqCZazuKxmHlhmX01bm4_Ii4YB6O_1KPCMlkvU_5012--KVRePYnN9OeQbfvE3TZJQ-N4SBpqNdv2o3_eINZNF1TULznhs-hEZPOo4kqFVQVC-jpsFKVAGeEeykueoMhrltL3OHM4vuXssYLn3bauNLCTAtc5s7f4evuHu6bspC4V_QxcGFcSiGTIgf_iB-zZ5KXDdncRf0MzNtT2OlIF4uo2z7s7h-RujMDUaEIiA14zGgYaKMVGJtSnXDqt0wMXNAYwxSwJqpDJrmg3PrCs4y2YmulspzxIKRLaCzNUrOMsDWhUpopnycei0UI9CSBc6mkiQErvYJ2380S5U5_I6r2zYWIShijEsbIwbiCdgDxqF6Exa_jVv84bgtNXh60o9PO-ckamvKBzbgsvnU0Nngamg1gI4Nks_ri3gBGKNey |
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=Efficient+in+situ+learning+of+hybrid+LIF+neurons+using+WTA+mechanism+for+high-speed+low-power+neuromorphic+systems&rft.jtitle=Physica+scripta&rft.au=Hussain%2C+Syed+Ali&rft.au=Prasad+V%2C+P+N+S+B+S+V&rft.au=Sanki%2C+Pradyut+Kumar&rft.date=2024-10-01&rft.pub=IOP+Publishing&rft.issn=0031-8949&rft.eissn=1402-4896&rft.volume=99&rft.issue=10&rft_id=info:doi/10.1088%2F1402-4896%2Fad79c5&rft.externalDocID=psad79c5 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-8949&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-8949&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-8949&client=summon |