A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification
Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data during the past several years. However, they are unable to construct the state-of-the-art CNNs due to their intrinsic architectures. In this r...
Saved in:
| Published in | IEEE transaction on neural networks and learning systems Vol. 30; no. 8; pp. 2295 - 2309 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.08.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data during the past several years. However, they are unable to construct the state-of-the-art CNNs due to their intrinsic architectures. In this regard, we propose a flexible CAE (FCAE) by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional CAE. We also design an architecture discovery method by exploiting particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed FCAE with much less computational resource and without any manual intervention. We test the proposed approach on four extensively used image classification data sets. Experimental results show that our proposed approach in this paper significantly outperforms the peer competitors including the state-of-the-art algorithms. |
|---|---|
| AbstractList | Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data during the past several years. However, they are unable to construct the state-of-the-art CNNs due to their intrinsic architectures. In this regard, we propose a flexible CAE (FCAE) by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional CAE. We also design an architecture discovery method by exploiting particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed FCAE with much less computational resource and without any manual intervention. We test the proposed approach on four extensively used image classification data sets. Experimental results show that our proposed approach in this paper significantly outperforms the peer competitors including the state-of-the-art algorithms.Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data during the past several years. However, they are unable to construct the state-of-the-art CNNs due to their intrinsic architectures. In this regard, we propose a flexible CAE (FCAE) by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional CAE. We also design an architecture discovery method by exploiting particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed FCAE with much less computational resource and without any manual intervention. We test the proposed approach on four extensively used image classification data sets. Experimental results show that our proposed approach in this paper significantly outperforms the peer competitors including the state-of-the-art algorithms. Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data during the past several years. However, they are unable to construct the state-of-the-art CNNs due to their intrinsic architectures. In this regard, we propose a flexible CAE (FCAE) by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional CAE. We also design an architecture discovery method by exploiting particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed FCAE with much less computational resource and without any manual intervention. We test the proposed approach on four extensively used image classification data sets. Experimental results show that our proposed approach in this paper significantly outperforms the peer competitors including the state-of-the-art algorithms. |
| Author | Xue, Bing Zhang, Mengjie Yen, Gary G. Sun, Yanan |
| Author_xml | – sequence: 1 givenname: Yanan orcidid: 0000-0001-6374-1429 surname: Sun fullname: Sun, Yanan email: yanan.sun@ecs.vuw.ac.nz organization: School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand – sequence: 2 givenname: Bing orcidid: 0000-0002-4865-8026 surname: Xue fullname: Xue, Bing email: bing.xue@ecs.vuw.ac.nz organization: School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand – sequence: 3 givenname: Mengjie orcidid: 0000-0003-4463-9538 surname: Zhang fullname: Zhang, Mengjie email: mengjie.zhang@ecs.vuw.ac.nz organization: School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand – sequence: 4 givenname: Gary G. orcidid: 0000-0001-8851-5348 surname: Yen fullname: Yen, Gary G. email: gyen@okstate.edu organization: School of Electrical and Computer Engineering, Oklahoma State University-Stillwater, Stillwater, OK, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30530340$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kc1u1DAUhS1UREvpC4CEIrFhk8HXjhN7OYwoVBq1SC0SO8tJrpErJx7sBGifHs8Ps-gCb2zJ3zlX95yX5GQMIxLyGugCgKoPd9fX69sFoyAXTEqAij8jZwxqVjIu5cnx3Xw_JRcp3dN8airqSr0gp5wKTnlFz4heFl9NnFznsbj9beJQ3GwmN7hHM7kwlh9Nwr649PjHtZlYhfFX8PP2y_hiOU8Bxy70GAsbYnE1mB-Z8SYlZ123c3hFnlvjE14c7nPy7fLT3epLub75fLVarsuugmYqgaLgQhhVVQxVC62lsjOqaVrJWmmVFH1dg2kQemWYbbjqK-TCcNu2vKOWn5P3e99NDD9nTJMeXOrQezNimJNmIEQORMo6o--eoPdhjnmhTLEapKqoEpl6e6DmdsBeb6IbTHzQ_6LLANsDXQwpRbRHBKjeVqR3FeltRfpQURbJJ6LOTbugpmic_7_0zV7qEPE4S4oGQAL_C5Mgneg |
| CODEN | ITNNAL |
| CitedBy_id | crossref_primary_10_1007_s40815_019_00697_9 crossref_primary_10_1093_bib_bbab090 crossref_primary_10_1016_j_eswa_2021_115945 crossref_primary_10_1016_j_eswa_2019_113113 crossref_primary_10_1016_j_neucom_2022_01_099 crossref_primary_10_3390_s22228881 crossref_primary_10_3390_axioms10030139 crossref_primary_10_1016_j_neucom_2021_04_111 crossref_primary_10_1109_TEVC_2023_3346969 crossref_primary_10_1093_jcde_qwac075 crossref_primary_10_1007_s10596_022_10177_z crossref_primary_10_20965_jaciii_2023_p0165 crossref_primary_10_1007_s00500_021_06711_3 crossref_primary_10_1016_j_ins_2021_01_064 crossref_primary_10_1109_TFUZZ_2024_3388023 crossref_primary_10_1007_s10462_021_09992_0 crossref_primary_10_1007_s10489_021_02589_8 crossref_primary_10_1016_j_compeleceng_2021_107108 crossref_primary_10_1109_ACCESS_2022_3177544 crossref_primary_10_1016_j_compbiomed_2023_107579 crossref_primary_10_1111_exsy_12690 crossref_primary_10_1109_TNNLS_2020_3027308 crossref_primary_10_1109_TCDS_2022_3179482 crossref_primary_10_1007_s10489_022_03422_6 crossref_primary_10_1109_ACCESS_2019_2937339 crossref_primary_10_1109_TII_2020_2998107 crossref_primary_10_3390_info14110604 crossref_primary_10_1007_s00521_020_04769_y crossref_primary_10_1109_TNNLS_2021_3109953 crossref_primary_10_3390_electronics12010113 crossref_primary_10_12720_jait_15_9_1011_1018 crossref_primary_10_3390_healthcare10040677 crossref_primary_10_1109_TEVC_2021_3079320 crossref_primary_10_1109_TEVC_2023_3245322 crossref_primary_10_1109_ACCESS_2020_3010543 crossref_primary_10_1109_TC_2024_3365949 crossref_primary_10_1631_FITEE_1900116 crossref_primary_10_1016_j_neunet_2025_107368 crossref_primary_10_1109_ACCESS_2020_2981141 crossref_primary_10_1016_j_patcog_2022_109215 crossref_primary_10_32604_cmc_2022_024232 crossref_primary_10_1016_j_asoc_2024_112392 crossref_primary_10_1016_j_dajour_2024_100470 crossref_primary_10_1109_LGRS_2024_3431216 crossref_primary_10_3390_en13040807 crossref_primary_10_1109_TNNLS_2021_3106399 crossref_primary_10_1016_j_ins_2024_121443 crossref_primary_10_1016_j_knosys_2022_110210 crossref_primary_10_1016_j_asej_2024_102734 crossref_primary_10_1016_j_ndteint_2024_103262 crossref_primary_10_1631_FITEE_2200515 crossref_primary_10_3390_math10193581 crossref_primary_10_1109_TEVC_2022_3217290 crossref_primary_10_1016_j_engappai_2023_107498 crossref_primary_10_1109_TEVC_2021_3068842 crossref_primary_10_1109_ACCESS_2020_3046078 crossref_primary_10_1016_j_asoc_2023_110079 crossref_primary_10_1016_j_asoc_2023_111049 crossref_primary_10_22399_ijcesen_493 crossref_primary_10_1016_j_mex_2024_102747 crossref_primary_10_1109_ACCESS_2019_2903015 crossref_primary_10_1109_TEVC_2021_3079985 crossref_primary_10_1155_2022_3571364 crossref_primary_10_1016_j_knosys_2024_112527 crossref_primary_10_1142_S021800142052014X crossref_primary_10_1016_j_ins_2022_05_100 crossref_primary_10_3390_electronics9111880 crossref_primary_10_1016_j_eswa_2023_120678 crossref_primary_10_1145_3603704 crossref_primary_10_1109_TNNLS_2021_3100554 crossref_primary_10_1109_TCYB_2023_3267109 crossref_primary_10_1016_j_artmed_2023_102571 crossref_primary_10_1016_j_neunet_2024_106104 crossref_primary_10_1109_TEVC_2021_3088631 crossref_primary_10_1007_s12555_021_0062_8 crossref_primary_10_1109_TEVC_2023_3252612 crossref_primary_10_1002_aisy_202300406 crossref_primary_10_1016_j_aej_2022_05_028 crossref_primary_10_1186_s41074_020_00065_9 crossref_primary_10_3390_sym14112323 crossref_primary_10_1016_j_asoc_2023_110412 crossref_primary_10_1109_TEVC_2020_3047220 crossref_primary_10_1145_3439730 crossref_primary_10_1145_3473330 crossref_primary_10_1007_s12046_021_01787_x crossref_primary_10_1109_ACCESS_2021_3106062 crossref_primary_10_1109_TNNLS_2023_3297624 crossref_primary_10_1109_TEVC_2023_3307245 crossref_primary_10_1142_S0129065721500350 crossref_primary_10_1016_j_patcog_2020_107794 crossref_primary_10_1177_09544119221135714 crossref_primary_10_1016_j_eswa_2019_04_051 crossref_primary_10_1109_TNNLS_2021_3107049 crossref_primary_10_1109_TCYB_2020_3035518 crossref_primary_10_1109_TEVC_2022_3189500 crossref_primary_10_1002_ett_4443 crossref_primary_10_1016_j_swevo_2024_101520 crossref_primary_10_1142_S012906572450014X |
| Cites_doi | 10.1145/2463372.2463459 10.1109/TEVC.2018.2808689 10.1109/SIS.2007.368035 10.1109/CVPR.2017.243 10.1109/TEVC.2013.2281543 10.1109/TCYB.2016.2536638 10.1109/CVPR.2010.5539957 10.1016/S0925-2312(02)00623-9 10.1109/CVPR.2016.90 10.1109/TMI.2003.815867 10.1109/CVPR.2009.5206577 10.1162/neco.2006.18.7.1527 10.1162/artl.2009.15.2.15202 10.1109/TNNLS.2016.2536741 10.1109/TAI.1997.632235 10.1007/978-3-642-35289-8_34 10.1109/5.726791 10.1109/CVPR.2007.383157 10.1109/TNNLS.2017.2695223 10.1109/CEC.2018.8477921 10.1016/S0042-6989(97)00169-7 10.1109/ICNN.1995.488968 10.1109/ICCV.2011.6126474 10.1109/TNNLS.2015.2469673 10.1007/BF00332918 10.1109/CVPR.2015.7298594 10.1126/science.1127647 10.1016/j.neucom.2007.10.013 10.1145/1553374.1553453 10.1109/TPAMI.2012.277 10.1016/j.ins.2013.05.031 10.1016/j.neucom.2004.07.002 10.1109/TSMCB.2003.818557 10.1038/nature14539 10.1109/CEC.2009.4983254 10.1109/TPAMI.2012.231 10.1109/MHS.1995.494215 10.1109/TSMCB.2012.2227469 10.1016/j.cviu.2005.09.012 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| DOI | 10.1109/TNNLS.2018.2881143 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Chemoreception Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Chemoreception Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed Materials Research Database |
| 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: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 2309 |
| ExternalDocumentID | 30530340 10_1109_TNNLS_2018_2881143 8571181 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Marsden Fund grantid: VUW1209; VUW1509; VUW1615 funderid: 10.13039/501100009193 – fundername: National Natural Science Foundation of China grantid: 61803277 funderid: 10.13039/501100001809 – fundername: Huawei Industry Fund grantid: E2880/3663 – fundername: National Natural Science Fund of China for Distinguished Young Scholar grantid: 61625204 – fundername: Victoria University of Wellington grantid: 209862/3580; 213150/3662 funderid: 10.13039/501100001538 |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION RIG NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| ID | FETCH-LOGICAL-c417t-10e5355a9442e9b1bf08ca977b82b8f985d661a7e1d9a2f739d4e35a3fbb3c0f3 |
| IEDL.DBID | RIE |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Thu Jul 10 22:23:23 EDT 2025 Mon Jun 30 05:07:04 EDT 2025 Thu Apr 03 07:26:22 EDT 2025 Tue Jul 01 00:27:29 EDT 2025 Thu Apr 24 22:58:13 EDT 2025 Wed Aug 27 05:50:40 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c417t-10e5355a9442e9b1bf08ca977b82b8f985d661a7e1d9a2f739d4e35a3fbb3c0f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-4865-8026 0000-0003-4463-9538 0000-0001-6374-1429 0000-0001-8851-5348 |
| PMID | 30530340 |
| PQID | 2261894095 |
| PQPubID | 85436 |
| PageCount | 15 |
| ParticipantIDs | ieee_primary_8571181 crossref_citationtrail_10_1109_TNNLS_2018_2881143 proquest_journals_2261894095 crossref_primary_10_1109_TNNLS_2018_2881143 pubmed_primary_30530340 proquest_miscellaneous_2155162886 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2019-08-01 |
| PublicationDateYYYYMMDD | 2019-08-01 |
| PublicationDate_xml | – month: 08 year: 2019 text: 2019-08-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Piscataway |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationTitleAlternate | IEEE Trans Neural Netw Learn Syst |
| PublicationYear | 2019 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref57 ref13 ref12 settles (ref48) 2003 ref15 glorot (ref66) 2011 hinton (ref3) 1994 ref53 rumelhart (ref1) 1988; 5 ref52 ref11 masci (ref16) 2011 ioffe (ref68) 2015 ref17 kavukcuoglu (ref23) 2010 ref19 schwenk (ref4) 1995 smolensky (ref18) 1986 krizhevsky (ref70) 2010; 40 ref51 ref50 lecun (ref7) 2015; 521 ref46 ref45 ref47 ref42 ref44 ref43 hutter (ref32) 2011; 5 bergstra (ref28) 2012; 13 coates (ref55) 2011 ref49 ref8 fei-fei (ref56) 2007; 106 ref9 krizhevsky (ref10) 2012 ref5 krizhevsky (ref54) 2009 ref35 ref34 srivastava (ref65) 2014; 15 bergstra (ref31) 2011 atanassov (ref58) 2009 ref33 sutton (ref59) 1998; 1 kim (ref40) 2015 abadi (ref69) 2016 ref2 ref39 ref38 real (ref37) 2017 glorot (ref64) 2010 rasmussen (ref29) 2006; 1 kingma (ref67) 2014 ref71 bengio (ref6) 2007 ref24 ref26 vincent (ref25) 2010; 11 ref20 ref63 simonyan (ref27) 2014 ref22 baker (ref36) 2017 ref21 krogh (ref61) 1992 mo?kus (ref30) 1975 fernando (ref41) 2016 weston (ref72) 2012 pass (ref14) 1997 ref60 ref62 |
| References_xml | – ident: ref39 doi: 10.1145/2463372.2463459 – start-page: 153 year: 2007 ident: ref6 article-title: Greedy layer-wise training of deep networks publication-title: Proc Adv Neural Inf Process Syst – volume: 15 start-page: 1929 year: 2014 ident: ref65 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – volume: 5 start-page: 507 year: 2011 ident: ref32 article-title: Sequential model-based optimization for general algorithm configuration publication-title: Proc LION – year: 2017 ident: ref36 article-title: Designing neural network architectures using reinforcement learning publication-title: Proc Int Conf Learning Represent – volume: 5 start-page: 1 year: 1988 ident: ref1 article-title: Learning representations by back-propagating errors publication-title: Modeling Cognition – ident: ref33 doi: 10.1109/TEVC.2018.2808689 – ident: ref63 doi: 10.1109/SIS.2007.368035 – volume: 1 year: 2006 ident: ref29 publication-title: Gaussian Processes for Machine Learning – year: 2014 ident: ref67 publication-title: Adam A method for stochastic optimization – ident: ref57 doi: 10.1109/CVPR.2017.243 – ident: ref53 doi: 10.1109/TEVC.2013.2281543 – ident: ref24 doi: 10.1109/TCYB.2016.2536638 – start-page: 992 year: 1995 ident: ref4 article-title: Transformation invariant autoassociation with application to handwritten character recognition publication-title: Proc Adv Neural Inf Process Syst – ident: ref20 doi: 10.1109/CVPR.2010.5539957 – ident: ref51 doi: 10.1016/S0925-2312(02)00623-9 – ident: ref26 doi: 10.1109/CVPR.2016.90 – volume: 40 year: 2010 ident: ref70 article-title: Convolutional deep belief networks on cifar-10 – start-page: 950 year: 1992 ident: ref61 article-title: A simple weight decay can improve generalization publication-title: Proc Adv Neural Inf Process Syst – year: 2017 ident: ref37 publication-title: Large-scale evolution of image classifiers – start-page: 215 year: 2011 ident: ref55 article-title: An analysis of single-layer networks in unsupervised feature learning publication-title: Proc 14th Int Conf Artif Intell Statist – ident: ref13 doi: 10.1109/TMI.2003.815867 – year: 1986 ident: ref18 article-title: Information processing in dynamical systems: Foundations of harmony theory – volume: 1 year: 1998 ident: ref59 publication-title: Reinforcement Learning An Introduction – ident: ref17 doi: 10.1109/CVPR.2009.5206577 – ident: ref8 doi: 10.1162/neco.2006.18.7.1527 – start-page: 200 year: 2003 ident: ref48 article-title: Comparison of genetic algorithm and particle swarm optimizer when evolving a recurrent neural network publication-title: Genetic and Evolutionary Computation – ident: ref38 doi: 10.1162/artl.2009.15.2.15202 – ident: ref15 doi: 10.1109/TNNLS.2016.2536741 – ident: ref52 doi: 10.1109/TAI.1997.632235 – start-page: 109 year: 2016 ident: ref41 article-title: Convolution by evolution: Differentiable pattern producing networks publication-title: Proc Genet Evol Comput Conf – start-page: 639 year: 2012 ident: ref72 article-title: Deep learning via semi-supervised embedding publication-title: Neural Networks Tricks of the Trade doi: 10.1007/978-3-642-35289-8_34 – start-page: 448 year: 2015 ident: ref68 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proc Int Conf Mach Learn – start-page: 1097 year: 2012 ident: ref10 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref9 doi: 10.1109/5.726791 – ident: ref71 doi: 10.1109/CVPR.2007.383157 – ident: ref34 doi: 10.1109/TNNLS.2017.2695223 – start-page: 160 year: 2015 ident: ref40 article-title: Deep clustered convolutional kernels publication-title: Feature Extraction Modern Questions and Challenge – ident: ref60 doi: 10.1109/CEC.2018.8477921 – ident: ref22 doi: 10.1016/S0042-6989(97)00169-7 – start-page: 1090 year: 2010 ident: ref23 article-title: Learning convolutional feature hierarchies for visual recognition publication-title: Proc Adv Neural Inf Process Syst – ident: ref42 doi: 10.1109/ICNN.1995.488968 – ident: ref21 doi: 10.1109/ICCV.2011.6126474 – year: 2009 ident: ref54 article-title: Learning multiple layers of features from tiny images – start-page: 315 year: 2011 ident: ref66 article-title: Deep sparse rectifier neural networks publication-title: Proc 14th Int Conf Artif Intell Statist – ident: ref35 doi: 10.1109/TNNLS.2015.2469673 – start-page: 249 year: 2010 ident: ref64 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref2 doi: 10.1007/BF00332918 – volume: 13 start-page: 281 year: 2012 ident: ref28 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – ident: ref12 doi: 10.1109/CVPR.2015.7298594 – ident: ref5 doi: 10.1126/science.1127647 – start-page: 3 year: 1994 ident: ref3 article-title: Autoencoders, minimum description length and Helmholtz free energy publication-title: Proc Adv Neural Inf Process Syst – start-page: 2546 year: 2011 ident: ref31 article-title: Algorithms for hyper-parameter optimization publication-title: Proc Adv Neural Inf Process Syst – year: 2014 ident: ref27 publication-title: Very Deep Convolutional Networks for Large-scale Image Recognition – ident: ref47 doi: 10.1016/j.neucom.2007.10.013 – start-page: 52 year: 2011 ident: ref16 article-title: Stacked convolutional auto-encoders for hierarchical feature extraction publication-title: Artificial Neural Networks in Machine Learning – year: 2016 ident: ref69 publication-title: Tensorflow Large-scale machine learning on heterogeneous distributed systems – start-page: 459 year: 2009 ident: ref58 article-title: Tuning the generation of Sobol sequence with Owen scrambling publication-title: Large-Scale Scientific Computing – ident: ref19 doi: 10.1145/1553374.1553453 – ident: ref62 doi: 10.1109/TPAMI.2012.277 – ident: ref46 doi: 10.1016/j.ins.2013.05.031 – ident: ref49 doi: 10.1016/j.neucom.2004.07.002 – ident: ref50 doi: 10.1109/TSMCB.2003.818557 – volume: 521 start-page: 436 year: 2015 ident: ref7 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – start-page: 65 year: 1997 ident: ref14 article-title: Comparing images using color coherence vectors publication-title: Proc 4th ACM Int Conf Multimedia – ident: ref45 doi: 10.1109/CEC.2009.4983254 – ident: ref11 doi: 10.1109/TPAMI.2012.231 – ident: ref43 doi: 10.1109/MHS.1995.494215 – ident: ref44 doi: 10.1109/TSMCB.2012.2227469 – volume: 11 start-page: 3371 year: 2010 ident: ref25 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – start-page: 400 year: 1975 ident: ref30 article-title: On Bayesian methods for seeking the extremum publication-title: Proc Optim Techn IFIP Tech Conf – volume: 106 start-page: 59 year: 2007 ident: ref56 article-title: Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories publication-title: Comput Vis Image Understand doi: 10.1016/j.cviu.2005.09.012 |
| SSID | ssj0000605649 |
| Score | 2.592004 |
| Snippet | Convolutional autoencoders (CAEs) have shown their remarkable performance in stacking to deep convolutional neural networks (CNNs) for classifying image data... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 2295 |
| SubjectTerms | Algorithms Artificial neural networks Classification Computer applications Computer architecture Convolution Convolutional autoencoder (CAE) Convolutional codes deep learning Image classification Neural networks Optimization Particle swarm optimization particle swarm optimization (PSO) Stacking |
| Title | A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification |
| URI | https://ieeexplore.ieee.org/document/8571181 https://www.ncbi.nlm.nih.gov/pubmed/30530340 https://www.proquest.com/docview/2261894095 https://www.proquest.com/docview/2155162886 |
| Volume | 30 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB61PXGhQHkECjISN8g2ju3YPpaKVUGwILWV9hbFjn0pm6CSgMSvZ-w4EUKAuEWKPXE045lv7HkAvPDcauopz5nxPudWmBztvMwltb6snC1pG6t9bqrzK_5uK7Z78GrJhXHOxeAztwqP8S6_7e0YjspOlJAhT3If9tFxm3K1lvOUAnF5FdFuSasyL5nczjkyhT653GzeX4RALrUqlUIfIPTPQVFHBR6OPX4xSbHHyt_hZjQ760P4MC94ija5Xo2DWdkfv9Vy_N8_ugO3E_4kp5PA3IU9192Dw7m3A0lb_QjqU_IpSRW5-N7c7MhHVC67lLWZv0bj15J1qKZpcMRZ331LMhyIj0Mf6mO2SBAxMXm7Q6VFYvvNEJgUKdyHq_Wby7PzPDVjyC2nckB17QRik0ZzXjptqPGFsg2iR6NKo7xWokVT30hHW92UXjLdcsdEw7wxzBaePYCDru_cIyCNVM6KwhTMKS5apYW0NExnDL1JqTKgMz9qmyqVh4YZn-vosRS6juysAzvrxM4MXi5zvkx1Ov45-ijwYhmZ2JDB8cz2Om3lrzXiU6o0usEig-fLa9yE4Wal6Vw_4ph434jEqwweTuKy0J6l7PGfv_kEbuHK9BRTeAwHw83oniLOGcyzKOA_AXZg9hA |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB6VcoALBQolUCBI3CDb2I5j-1gqVlvYLkjdSnuLYse-wGZRSUDi1zN2nAghQNwiZTxxNOOZz_Y8AF66wijiSJEx7VxWGK4z9PMiE8Q4WlpDSROqfa7KxVXxbsM3e_B6yoWx1obgMzvzj-Euv9mZ3h-VnUgufJ7kDbiJfp_TIVtrOlHJEZmXAe9SUtKMMrEZs2RydbJerZaXPpRLzqiUuAvwHXRQ2dGE-4OPX5xS6LLyd8AZHM_8AC7GKQ_xJp9mfadn5sdv1Rz_95_uwp2IQNPTQWXuwZ5t78PB2N0hjYv9EKrT9GPUq_Tye329TT-gednGvM3sDbq_Jp37epoaKc527beoxZ553-18hcwGGSIqTs-3aLbS0IDThyYFDg_gav52fbbIYjuGzBREdGiwLUd0UquioFZpol0uTY34UUuqpVOSN-jsa2FJo2rqBFNNYRmvmdOamdyxh7Df7lr7CNJaSGt4rnNmZcEbqbgwxA9nDPeTQiZARnlUJtYq9y0zPldhz5KrKoiz8uKsojgTeDWN-TJU6vgn9aGXxUQZxZDA8Sj2Ki7mrxUiVCIVboR5Ai-m17gM_d1K3dpdjzThxhGZlwkcDeoy8R617PGfv_kcbi3WF8tqeb56_wRu4yzVEGF4DPvddW-fIurp9LOg7D8BdcT5Wg |
| 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=A+Particle+Swarm+Optimization-Based+Flexible+Convolutional+Autoencoder+for+Image+Classification&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Sun%2C+Yanan&rft.au=Xue%2C+Bing&rft.au=Zhang%2C+Mengjie&rft.au=Yen%2C+Gary+G&rft.date=2019-08-01&rft.issn=2162-2388&rft.eissn=2162-2388&rft.volume=30&rft.issue=8&rft.spage=2295&rft_id=info:doi/10.1109%2FTNNLS.2018.2881143&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |