Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization
We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classi...
Uložené v:
| Vydané v: | Neural networks Ročník 103; s. 118 - 127 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
Elsevier Ltd
01.07.2018
|
| Predmet: | |
| ISSN: | 0893-6080, 1879-2782, 1879-2782 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. |
|---|---|
| AbstractList | We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications.We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. |
| Author | Rajendran, Bipin Kulkarni, Shruti R. |
| Author_xml | – sequence: 1 givenname: Shruti R. orcidid: 0000-0001-6894-9851 surname: Kulkarni fullname: Kulkarni, Shruti R. – sequence: 2 givenname: Bipin surname: Rajendran fullname: Rajendran, Bipin email: bipin@njit.edu |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/29674234$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkb1uFDEUhS0URDaBN0BoSpoZru3dsU2BhCL-pEgUgdpyPNcbb2btwfYkChUPkSfMk-Blsw0FVLc53yfdc07IUYgBCXlJoaNA-zebLuAcsHQMqOyAd0DVE7KgUqiWCcmOyAKk4m0PEo7JSc4bAOjlkj8jx0z1Ysn4ckGuLiZ_7cO6qbJkxnrKbUzXuXExNVcmDLfJl4KhGfzalyahjevgi4_h4df9xTxhuvEZh2ZEk8LOU5GDpIlT8Vv_0-ziz8lTZ8aMLx7vKfn-8cO3s8_t-ddPX87en7eW96y0SlgObhCWOenoSrDBOQXDinJ-aQUDZlBSR1V9cGW4kgqsEih6S4UAtXL8lLzee6cUf8yYi976bHEcTcA4Z10VUvW95LJGXz1G58stDnpKfmvSnT60UwNv9wGbYs4Jnba-_PmmJONHTUHvptAbvZ9C76bQwHWdosLLv-CD_z_Yuz2GtaQbj0ln6zFYHHwtv-gh-n8LfgMNaKgq |
| CitedBy_id | crossref_primary_10_1007_s00521_023_09186_5 crossref_primary_10_1155_2019_8429120 crossref_primary_10_1109_TNNLS_2021_3055421 crossref_primary_10_1016_j_procs_2020_04_206 crossref_primary_10_1162_neco_a_01499 crossref_primary_10_1007_s13369_021_05471_4 crossref_primary_10_1038_s41598_020_64878_5 crossref_primary_10_1016_j_patcog_2019_05_015 crossref_primary_10_46670_JSST_2021_30_1_20 crossref_primary_10_1002_advs_202407870 crossref_primary_10_1016_j_knosys_2020_106157 crossref_primary_10_1007_s11071_021_07177_6 crossref_primary_10_1002_EXP_20220162 crossref_primary_10_1007_s44163_022_00046_0 crossref_primary_10_2478_jaiscr_2019_0009 crossref_primary_10_1007_s11760_020_01703_6 crossref_primary_10_1038_s41598_020_60572_8 crossref_primary_10_3389_fnins_2018_00774 crossref_primary_10_1007_s13735_023_00291_8 crossref_primary_10_1088_1674_1056_abd2a5 crossref_primary_10_1016_j_neucom_2023_02_026 crossref_primary_10_1109_TAI_2022_3221688 crossref_primary_10_1109_TED_2024_3487085 crossref_primary_10_1364_PRJ_413742 crossref_primary_10_1109_TNNLS_2020_3006263 crossref_primary_10_1177_14727978241302442 crossref_primary_10_1016_j_asoc_2019_04_006 crossref_primary_10_1109_TNNLS_2024_3353571 crossref_primary_10_1109_TED_2019_2898402 crossref_primary_10_3390_s21186273 crossref_primary_10_1155_2020_8851351 crossref_primary_10_1038_s41467_018_07682_0 crossref_primary_10_3389_frai_2022_680165 crossref_primary_10_3390_bdcc7020110 crossref_primary_10_3390_s20174715 crossref_primary_10_1007_s10489_018_1373_1 crossref_primary_10_1016_j_neunet_2019_06_001 crossref_primary_10_1007_s00521_022_06936_9 crossref_primary_10_1016_j_applthermaleng_2023_121256 crossref_primary_10_1134_S1560354724560016 crossref_primary_10_1038_s43588_021_00184_y crossref_primary_10_1002_aelm_202001241 crossref_primary_10_1109_TCDS_2021_3140115 crossref_primary_10_1109_TNNLS_2020_3015208 crossref_primary_10_1016_j_engappai_2023_106744 crossref_primary_10_1038_s42256_020_0187_0 crossref_primary_10_1007_s41870_022_01076_8 crossref_primary_10_1109_TCDS_2019_2909355 crossref_primary_10_1007_s11571_020_09605_6 crossref_primary_10_1021_acsaelm_4c02015 crossref_primary_10_1016_j_neunet_2020_02_011 crossref_primary_10_1109_MNANO_2021_3098219 crossref_primary_10_1016_j_imavis_2019_04_007 crossref_primary_10_1016_j_patcog_2021_108513 crossref_primary_10_1145_3304103 crossref_primary_10_1007_s10772_020_09735_6 crossref_primary_10_1016_j_neucom_2024_127598 crossref_primary_10_1016_j_neucom_2024_128483 crossref_primary_10_3389_fnins_2022_926256 crossref_primary_10_3389_fnins_2022_857513 crossref_primary_10_1088_1361_6528_ad6997 crossref_primary_10_1016_j_optmat_2025_116829 crossref_primary_10_3390_fractalfract8120689 crossref_primary_10_1007_s12559_022_10045_z crossref_primary_10_1109_TGRS_2024_3516742 crossref_primary_10_3390_nano14080697 crossref_primary_10_1016_j_ipm_2022_103088 crossref_primary_10_1007_s00521_025_11066_z crossref_primary_10_1007_s11063_020_10397_3 crossref_primary_10_1016_j_jclepro_2018_10_254 crossref_primary_10_1093_pnasnexus_pgae488 crossref_primary_10_1007_s12046_020_01410_5 crossref_primary_10_1007_s12293_022_00373_w crossref_primary_10_1109_TNNLS_2021_3109064 crossref_primary_10_1002_mma_10000 crossref_primary_10_1016_j_neucom_2020_10_100 crossref_primary_10_1109_TED_2023_3317357 crossref_primary_10_1155_2023_2753941 crossref_primary_10_1109_JSEN_2021_3098013 crossref_primary_10_3389_fnins_2019_00405 crossref_primary_10_1007_s42979_022_01259_x crossref_primary_10_1016_j_energy_2020_117072 crossref_primary_10_1007_s11432_019_1468_0 crossref_primary_10_1109_TCYB_2021_3109566 |
| Cites_doi | 10.1073/pnas.2536316100 10.1109/IJCNN.2015.7280618 10.1109/IJCNN.2016.7727509 10.1109/CVPR.2012.6248110 10.1016/j.neunet.2015.09.011 10.1109/IJCNN.2016.7727212 10.1371/journal.pone.0040233 10.1016/j.neunet.2014.01.006 10.1109/TNNLS.2018.2826721 10.1038/ncomms13276 10.1109/JPROC.2014.2304638 10.1142/S0129065712500128 10.3389/fncel.2016.00239 10.1613/jair.4992 10.1109/IJCNN.2017.7966099 10.1126/science.1254642 10.3389/fncom.2015.00099 10.3389/fnins.2016.00508 10.1016/S0361-9230(99)00161-6 10.1109/TNNLS.2015.2404938 10.1109/JPROC.2014.2313565 10.1109/IJCNN.2015.7280696 10.1162/neco.2006.18.7.1527 10.1007/s00359-006-0117-6 10.1371/journal.pcbi.0030031 10.1109/TNNLS.2016.2541339 10.1162/neco.2007.19.11.2881 10.3389/fnins.2017.00682 10.1016/S0925-2312(02)00838-X 10.3389/fnins.2015.00222 10.1109/TNNLS.2015.2501322 10.1016/S0925-2312(01)00658-0 10.1109/5.726791 10.1109/UKRICIS.2010.5898113 10.3389/fnins.2016.00333 10.1016/S0893-6080(97)00011-7 10.1113/jphysiol.1968.sp008455 10.1109/MSP.2012.2205597 10.1109/CVPR.2014.223 10.1371/journal.pone.0078318 10.3389/fnins.2013.00153 10.1016/j.neucom.2004.10.031 10.1007/s11263-014-0788-3 10.1109/FSKD.2016.7603446 10.1523/JNEUROSCI.1677-11.2011 10.1016/j.tins.2009.12.001 10.1038/nn1643 10.1016/j.neucom.2017.02.013 10.1109/TNNLS.2016.2582517 10.3389/fnins.2015.00141 10.1109/TNNLS.2015.2509479 10.1162/neco.2009.11-08-901 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier Ltd Copyright © 2018 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2018 Elsevier Ltd – notice: Copyright © 2018 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.neunet.2018.03.019 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| 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: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 127 |
| ExternalDocumentID | 29674234 10_1016_j_neunet_2018_03_019 S0893608018301126 |
| Genre | Journal Article |
| 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- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD BNPGV CGR CUY CVF ECM EIF NPM SSH 7X8 |
| ID | FETCH-LOGICAL-c362t-97c30fd7c2f8f1572dff90d5133bc7202ae81f197825a39890c97e76c177095f3 |
| ISICitedReferencesCount | 107 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000432819400012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Mon Sep 29 06:02:56 EDT 2025 Thu Apr 03 07:06:25 EDT 2025 Sat Nov 29 07:12:07 EST 2025 Tue Nov 18 22:18:35 EST 2025 Fri Feb 23 02:28:38 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Spiking neurons Pattern recognition Neural networks Supervised learning Approximate computing Neuromorphic computing |
| Language | English |
| License | Copyright © 2018 Elsevier Ltd. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c362t-97c30fd7c2f8f1572dff90d5133bc7202ae81f197825a39890c97e76c177095f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-6894-9851 |
| PMID | 29674234 |
| PQID | 2028966838 |
| PQPubID | 23479 |
| PageCount | 10 |
| ParticipantIDs | proquest_miscellaneous_2028966838 pubmed_primary_29674234 crossref_citationtrail_10_1016_j_neunet_2018_03_019 crossref_primary_10_1016_j_neunet_2018_03_019 elsevier_sciencedirect_doi_10_1016_j_neunet_2018_03_019 |
| PublicationCentury | 2000 |
| PublicationDate | July 2018 2018-07-00 2018-Jul 20180701 |
| PublicationDateYYYYMMDD | 2018-07-01 |
| PublicationDate_xml | – month: 07 year: 2018 text: July 2018 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2018 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Masquelier, Thorpe (b41) 2007; 3 Roy, Basu (b51) 2017; 28 Lecun, Bottou, Bengio, Haffner (b36) 1998; 86 Mozafari, M., Kheradpisheh, S. R., Masquelier, T., Nowzari-Dalini, A., & Ganjtabesh, M. (2017). First-spike based visual categorization using reward-modulated stdp. arxiv preprint Cao, Chen, Khosla (b8) 2015; 113 Florian (b13) 2012; 7 Rueckauer, Lungu, Hu, Pfeiffer, Liu (b53) 2017; 11 Brader, Senn, Fusi (b6) 2007; 19 Ciregan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. In Crotty, Levy (b10) 2005; 65 Kasabov, Scott, Tu, Marks, Sengupta, Capecci (b30) 2016; 78 Kulkarni, Rajendran (b34) 2015 Kheradpisheh, Ganjtabesh, Thorpe, Masquelier (b32) 2017 Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In Diehl, Cook (b11) 2015; 9 Ponulak, Kasinski (b48) 2010; 22 pp. 1725–1732 Stromatias, Neil, Pfeiffer, Galluppi, Furber, Liu (b56) 2015; 9 Wan, Zeiler, Zhang, Cun, Fergus (b62) 2013; vol. 28 Goodfellow, Warde-Farley, Mirza, Courville, Bengio (b20) 2013; vol. 28 Hopfield, Brody (b24) 2004; 101 Merolla, Arthur, Alvarez-Icaza, Cassidy, Sawada, Akopyan (b42) 2014; 345 Hinton, Osindero, Teh (b23) 2006; 18 Krizhevsky, Sutskever, Hinton (b33) 2012 Yu, Tang, Tan, Li (b68) 2013; 8 Shoham, O’Connor, Segev (b55) 2006; 192 Hubel, Wiesel (b25) 1968; 195 Goldberg (b18) 2016; 57 Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. URL . Mohemmed, Schliebs, Matsuda, Kasabov (b43) 2012; 22 Gokmen, Vlasov (b17) 2016; 10 Lillicrap, Cownden, Tweed, Akerman (b39) 2016 Panzeri, Brunel, Logothetis, Kayser (b47) 2010; 33 Allred, J. M., & Roy, K. (2016). Unsupervised incremental STDP learning using forced firing of dormant or idle neurons. In Calderón, A., Roa, S., & Victorino, J. (2003). Handwritten digit recognition using convolutional neural networks and gabor filters. In pp. 1773–1777 Furber, Galluppi, Temple, Plana (b14) 2014; 102 Lee, Kukreja, Thakor (b38) 2017; 28 Lee, Delbruck, Pfeiffer (b37) 2016; 10 Tapson, J., Cohen, G., Afshar, S., Stiefel, K., Buskila, Y., & Wang, R. et al. (2013). Synthesis of neural networks for spatio-temporal spike pattern recognition and processing. arXiv preprint Gabbiani, Metzner (b15) 1999; 202 Tavanaei, A., & Maida, A. S. (2017). Multi-layer unsupervised learning in a spiking convolutional neural network. In Roxin, Brunel, Hansel, Mongillo, van Vreeswijk (b50) 2011; 31 Wang, Belatreche, Maguire, McGinnity (b65) 2017; 28 Maass (b40) 1997; 10 Gehlhaar (b16) 2014 Benjamin, Gao, McQuinn, Choudhary, Chandrasekaran, Bussat (b4) 2014; 102 Xie, Qu, Yi, Kurths (b67) 2017; 28 Hunsberger, E., & Eliasmith, C. (2016). Training spiking deep networks for neuromorphic hardware. arXiv preprint Lazar, Simonyi, Tóth (b35) 2005 pp. 3642–3649 Schreiber, Fellous, Whitmer, Tiesinga, Sejnowski (b54) 2003; 52 Bohte, Kok, La Poutre (b5) 2002; 48 Qiao, Mostafa, Corradi, Osswald, Stefanini, Sumislawska (b49) 2015; 9 Abbott (b1) 1999; 50 Panda, P., & Roy, K. (2016). Unsupervised regenerative learning of hierarchical features in Spiking Deep Networks for object recognition. In Diehl, P. U., Neil, D., Binas, J., Cook, M., Liu, S. C., & Pfeiffer, M. (2015). Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In Kasabov (b29) 2014; 52 Khan, Ghani, Khurram (b31) 2017; 239 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 pp. 2023–2030 Tapson, De Chazal, van Schaik (b60) 2015 Takuya, T., Haruhiko, T., Hiroharu, K., & Shinji, T. (2016). A training algorithm for spike sequence in spiking neural networks –A discussion on growing network for stable training performance. In Wang, Belatreche, Maguire, McGinnity (b64) 2015 pp. 1–8 Taherkhani, Belatreche, Li, Maguire (b57) 2015; 26 Wang, Ke, Guang, Chen, Yin, Deng (b66) 2016; 10 Hinton, Deng, Yu, Dahl, Mohamed, Jaitly (b22) 2012; 29 pp. 299–306 Gutig, Sompolinsky (b21) 2006; 9 Hunsberger (b27) 2018 [q-bio.NC]. pp. 1–6 NAE (2009). National academy of engineering - Reverse-engineer the brain. Available at Wang, J., Belatreche, A., Maguire, L., & McGinnity, M. (2010). Online versus offline learning for spiking neural networks: A review and new strategies. In Anwani, N., & Rajendran, B. (2015). NormAD - Normalized Approximate Descent based supervised learning rule for spiking neurons. In Bohte (10.1016/j.neunet.2018.03.019_b5) 2002; 48 10.1016/j.neunet.2018.03.019_b19 Lee (10.1016/j.neunet.2018.03.019_b38) 2017; 28 Brader (10.1016/j.neunet.2018.03.019_b6) 2007; 19 Panzeri (10.1016/j.neunet.2018.03.019_b47) 2010; 33 Cao (10.1016/j.neunet.2018.03.019_b8) 2015; 113 Maass (10.1016/j.neunet.2018.03.019_b40) 1997; 10 10.1016/j.neunet.2018.03.019_b52 Gutig (10.1016/j.neunet.2018.03.019_b21) 2006; 9 Gehlhaar (10.1016/j.neunet.2018.03.019_b16) 2014 10.1016/j.neunet.2018.03.019_b58 10.1016/j.neunet.2018.03.019_b59 10.1016/j.neunet.2018.03.019_b12 Ponulak (10.1016/j.neunet.2018.03.019_b48) 2010; 22 Rueckauer (10.1016/j.neunet.2018.03.019_b53) 2017; 11 10.1016/j.neunet.2018.03.019_b28 Xie (10.1016/j.neunet.2018.03.019_b67) 2017; 28 Wang (10.1016/j.neunet.2018.03.019_b65) 2017; 28 Wang (10.1016/j.neunet.2018.03.019_b66) 2016; 10 Stromatias (10.1016/j.neunet.2018.03.019_b56) 2015; 9 Taherkhani (10.1016/j.neunet.2018.03.019_b57) 2015; 26 Wan (10.1016/j.neunet.2018.03.019_b62) 2013; vol. 28 Mohemmed (10.1016/j.neunet.2018.03.019_b43) 2012; 22 Yu (10.1016/j.neunet.2018.03.019_b68) 2013; 8 Lee (10.1016/j.neunet.2018.03.019_b37) 2016; 10 Lecun (10.1016/j.neunet.2018.03.019_b36) 1998; 86 10.1016/j.neunet.2018.03.019_b61 Qiao (10.1016/j.neunet.2018.03.019_b49) 2015; 9 10.1016/j.neunet.2018.03.019_b63 Kheradpisheh (10.1016/j.neunet.2018.03.019_b32) 2017 Krizhevsky (10.1016/j.neunet.2018.03.019_b33) 2012 Hinton (10.1016/j.neunet.2018.03.019_b23) 2006; 18 Hinton (10.1016/j.neunet.2018.03.019_b22) 2012; 29 10.1016/j.neunet.2018.03.019_b26 Crotty (10.1016/j.neunet.2018.03.019_b10) 2005; 65 Shoham (10.1016/j.neunet.2018.03.019_b55) 2006; 192 Wang (10.1016/j.neunet.2018.03.019_b64) 2015 Goodfellow (10.1016/j.neunet.2018.03.019_b20) 2013; vol. 28 Lazar (10.1016/j.neunet.2018.03.019_b35) 2005 Gabbiani (10.1016/j.neunet.2018.03.019_b15) 1999; 202 Hopfield (10.1016/j.neunet.2018.03.019_b24) 2004; 101 Hunsberger (10.1016/j.neunet.2018.03.019_b27) 2018 Hubel (10.1016/j.neunet.2018.03.019_b25) 1968; 195 Kulkarni (10.1016/j.neunet.2018.03.019_b34) 2015 Furber (10.1016/j.neunet.2018.03.019_b14) 2014; 102 Abbott (10.1016/j.neunet.2018.03.019_b1) 1999; 50 Khan (10.1016/j.neunet.2018.03.019_b31) 2017; 239 Roxin (10.1016/j.neunet.2018.03.019_b50) 2011; 31 Masquelier (10.1016/j.neunet.2018.03.019_b41) 2007; 3 Kasabov (10.1016/j.neunet.2018.03.019_b29) 2014; 52 Tapson (10.1016/j.neunet.2018.03.019_b60) 2015 Benjamin (10.1016/j.neunet.2018.03.019_b4) 2014; 102 Diehl (10.1016/j.neunet.2018.03.019_b11) 2015; 9 Roy (10.1016/j.neunet.2018.03.019_b51) 2017; 28 Goldberg (10.1016/j.neunet.2018.03.019_b18) 2016; 57 Lillicrap (10.1016/j.neunet.2018.03.019_b39) 2016 Gokmen (10.1016/j.neunet.2018.03.019_b17) 2016; 10 Kasabov (10.1016/j.neunet.2018.03.019_b30) 2016; 78 Schreiber (10.1016/j.neunet.2018.03.019_b54) 2003; 52 10.1016/j.neunet.2018.03.019_b2 Merolla (10.1016/j.neunet.2018.03.019_b42) 2014; 345 10.1016/j.neunet.2018.03.019_b46 10.1016/j.neunet.2018.03.019_b3 10.1016/j.neunet.2018.03.019_b7 10.1016/j.neunet.2018.03.019_b44 10.1016/j.neunet.2018.03.019_b9 Florian (10.1016/j.neunet.2018.03.019_b13) 2012; 7 10.1016/j.neunet.2018.03.019_b45 |
| References_xml | – volume: 202 start-page: 1267 year: 1999 end-page: 1279 ident: b15 article-title: Encoding and processing of sensory information in neuronal spike trains publication-title: Journal of Fish Biology – year: 2016 ident: b39 article-title: Random synaptic feedback weights support error backpropagation for deep learning publication-title: Nature Communications – reference: (pp. 1–8), – reference: Calderón, A., Roa, S., & Victorino, J. (2003). Handwritten digit recognition using convolutional neural networks and gabor filters. In – volume: 52 start-page: 925 year: 2003 end-page: 931 ident: b54 article-title: A new correlation-based measure of spike timing reliability publication-title: Neurocomputing – volume: 78 start-page: 1 year: 2016 end-page: 14 ident: b30 article-title: Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: design methodology and selected applications publication-title: Neural Networks – reference: [q-bio.NC]. – volume: 33 start-page: 111 year: 2010 end-page: 120 ident: b47 article-title: Sensory neural codes using multiplexed temporal scales publication-title: Trends in Neurosciences – volume: 195 start-page: 215 year: 1968 end-page: 243 ident: b25 article-title: Receptive fields and functional architecture of monkey striate cortex publication-title: The Journal of Physiology – volume: 239 start-page: 153 year: 2017 end-page: 164 ident: b31 article-title: Population coding for neuromorphic hardware publication-title: Neurocomputing – year: 2017 ident: b32 article-title: STDP-based spiking deep convolutional neural networks for object recognition publication-title: Neural Networks – reference: NAE (2009). National academy of engineering - Reverse-engineer the brain. Available at – reference: Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. URL – volume: vol. 28 start-page: 1319 year: 2013 end-page: 1327 ident: b20 article-title: Maxout networks publication-title: Proceedings of the 30th international conference on machine learning – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: b36 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE – volume: 28 start-page: 900 year: 2017 end-page: 910 ident: b51 article-title: An online unsupervised structural plasticity algorithm for spiking neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 345 start-page: 668 year: 2014 end-page: 673 ident: b42 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science – year: 2018 ident: b27 article-title: Spiking deep neural networks: Engineered and biological approaches to object recognition – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: b23 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation – volume: 52 start-page: 62 year: 2014 end-page: 76 ident: b29 article-title: NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data publication-title: Neural Networks – start-page: 259 year: 2015 end-page: 267 ident: b64 article-title: SpikeComp: An evolving spiking neural network with adaptive compact structure for pattern classification publication-title: Neural information processing: 22nd international conference, ICONIP 2015, Istanbul, Turkey, November 9-12, 2015, Proceedings, Part II – reference: Takuya, T., Haruhiko, T., Hiroharu, K., & Shinji, T. (2016). A training algorithm for spike sequence in spiking neural networks –A discussion on growing network for stable training performance. In – reference: Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In – year: 2005 ident: b35 article-title: Time encoding of bandlimited signals, an overview publication-title: Proceedings of conference on telecommunication systems, modeling and analysis – volume: 19 start-page: 2881 year: 2007 end-page: 2912 ident: b6 article-title: Learning real-world stimuli in a neural network with spike-driven synaptic dynamics publication-title: Neural Computation – volume: 28 start-page: 1411 year: 2017 end-page: 1424 ident: b67 article-title: Efficient training of supervised spiking neural network via accurate synaptic-efficiency adjustment method publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 8 start-page: 1 year: 2013 end-page: 16 ident: b68 article-title: Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns publication-title: Plos One – volume: 9 start-page: 222 year: 2015 ident: b56 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: Tavanaei, A., & Maida, A. S. (2017). Multi-layer unsupervised learning in a spiking convolutional neural network. In – volume: 101 start-page: 337 year: 2004 end-page: 342 ident: b24 article-title: Learning rules and network repair in spike-timing-based computation networks publication-title: Proceedings of the National Academy of Sciences – start-page: 41 year: 2015 end-page: 49 ident: b60 article-title: Explicit computation of input weights in extreme learning machines publication-title: Proceedings of ELM-2014 Volume 1:: Algorithms and theories – volume: 10 start-page: 239 year: 2016 ident: b66 article-title: Firing frequency maxima of fast-spiking neurons in human, monkey, and mouse neocortex publication-title: Frontiers in Cellular Neuroscience – reference: Hunsberger, E., & Eliasmith, C. (2016). Training spiking deep networks for neuromorphic hardware. arXiv preprint – volume: 11 start-page: 682 year: 2017 ident: b53 article-title: Conversion of continuous-valued deep networks to efficient event-driven networks for image classification publication-title: Frontiers in Neuroscience – volume: 26 start-page: 3137 year: 2015 end-page: 3149 ident: b57 article-title: DL-ReSuMe: A delay learning-based remote supervised method for spiking neurons publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: (pp. 1773–1777) – reference: Mozafari, M., Kheradpisheh, S. R., Masquelier, T., Nowzari-Dalini, A., & Ganjtabesh, M. (2017). First-spike based visual categorization using reward-modulated stdp. arxiv preprint – reference: Wang, J., Belatreche, A., Maguire, L., & McGinnity, M. (2010). Online versus offline learning for spiking neural networks: A review and new strategies. In – reference: (pp. 3642–3649), – volume: 28 start-page: 849 year: 2017 end-page: 861 ident: b38 article-title: CONE: Convex-optimized-synaptic efficacies for temporally precise spike mapping publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Diehl, P. U., Neil, D., Binas, J., Cook, M., Liu, S. C., & Pfeiffer, M. (2015). Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In – start-page: 149 year: 2015 end-page: 158 ident: b34 article-title: Scalable digital CMOS Architecture for Spike based Supervised Learning publication-title: Engineering applications of neural networks: 16th international conference, EANN 2015, Rhodes, Greece, September 25-28 2015. Proceedings – volume: 22 year: 2012 ident: b43 article-title: SPAN: Spike pattern association neuron for learning spatio-temporal spike patterns publication-title: International Journal of Neural Systems – volume: 22 start-page: 467 year: 2010 end-page: 510 ident: b48 article-title: Supervised learning in spiking neural networks with ReSuMe: Sequence learning, classification, and spike shifting publication-title: Neural Computation – reference: (pp. 1725–1732), – volume: 29 start-page: 82 year: 2012 end-page: 97 ident: b22 article-title: Deep Neural networks for acoustic modeling in speech recognition: The shared views of four research groups publication-title: IEEE Signal Processing Magazine – volume: 3 start-page: 1 year: 2007 end-page: 11 ident: b41 article-title: Unsupervised learning of visual features through spike timing dependent plasticity publication-title: PLOS Computational Biology – volume: 28 start-page: 30 year: 2017 end-page: 43 ident: b65 article-title: Spiketemp: An enhanced rank-order-based learning approach for spiking neural networks with adaptive structure publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 10 start-page: 508 year: 2016 ident: b37 article-title: Training deep spiking neural networks using backpropagation publication-title: Frontiers in Neuroscience – volume: 192 start-page: 777 year: 2006 end-page: 784 ident: b55 article-title: How silent is the brain: is there a “dark matter” problem in neuroscience? publication-title: Journal of Comparative Physiology A – reference: (pp. 2023–2030), – volume: 113 start-page: 54 year: 2015 end-page: 66 ident: b8 article-title: Spiking deep convolutional neural networks for energy-efficient object recognition publication-title: International Journal of Computer Vision – volume: 9 start-page: 99 year: 2015 ident: b11 article-title: Unsupervised learning of digit recognition using spike-timing-dependent plasticity publication-title: Frontiers in Computational Neuroscience – reference: (pp. 1–6), – start-page: 1097 year: 2012 end-page: 1105 ident: b33 article-title: ImageNet Classification with Deep Convolutional Neural Networks publication-title: Advances in neural information processing systems 25 – volume: 10 start-page: 333 year: 2016 ident: b17 article-title: Acceleration of deep neural network training with resistive cross-point devices: Design considerations publication-title: Frontiers in Neuroscience – 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 – reference: Allred, J. M., & Roy, K. (2016). Unsupervised incremental STDP learning using forced firing of dormant or idle neurons. In – reference: . – reference: Ciregan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. In – volume: 7 start-page: e40233 year: 2012 ident: b13 article-title: The chronotron: A neuron that learns to fire temporally precise spike patterns publication-title: PloS One – volume: 9 start-page: 420 year: 2006 end-page: 428 ident: b21 article-title: The tempotron: a neuron that learns spike timing-based decisions publication-title: Nature Neuroscience – reference: Tapson, J., Cohen, G., Afshar, S., Stiefel, K., Buskila, Y., & Wang, R. et al. (2013). Synthesis of neural networks for spatio-temporal spike pattern recognition and processing. arXiv preprint – start-page: 317 year: 2014 end-page: 318 ident: b16 article-title: Neuromorphic processing: A new frontier in scaling computer architecture publication-title: Proceedings of the 19th international conference on architectural support for programming languages and operating systems – volume: 9 start-page: 141 year: 2015 ident: b49 article-title: A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses publication-title: Frontiers in Neuroscience – volume: 31 start-page: 16217 year: 2011 end-page: 16226 ident: b50 article-title: On the distribution of firing rates in networks of cortical neurons publication-title: Journal of Neuroscience – volume: 10 start-page: 1659 year: 1997 end-page: 1671 ident: b40 article-title: Networks of spiking neurons: The third generation of neural network models publication-title: Neural Networks – reference: Anwani, N., & Rajendran, B. (2015). NormAD - Normalized Approximate Descent based supervised learning rule for spiking neurons. In – reference: (pp. 299–306), – volume: 48 start-page: 17 year: 2002 end-page: 37 ident: b5 article-title: Error-backpropagation in temporally encoded networks of spiking neurons publication-title: Neurocomputing – volume: 57 start-page: 345 year: 2016 end-page: 420 ident: b18 article-title: A Primer on neural network models for natural language processing publication-title: Journal of Artificial Intelligence Research (JAIR) – volume: 102 start-page: 699 year: 2014 end-page: 716 ident: b4 article-title: Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations publication-title: Proceedings of the IEEE – reference: Panda, P., & Roy, K. (2016). Unsupervised regenerative learning of hierarchical features in Spiking Deep Networks for object recognition. In – volume: 50 start-page: 303 year: 1999 end-page: 304 ident: b1 article-title: Lapicque’s introduction of the integrate-and-fire model neuron (1907) publication-title: Brain Research Bulletin – volume: 65 start-page: 371 year: 2005 end-page: 378 ident: b10 article-title: Energy-efficient interspike interval codes publication-title: Neurocomputing – volume: 102 start-page: 652 year: 2014 end-page: 665 ident: b14 article-title: The SpiNNaker Project publication-title: Proceedings of the IEEE – volume: vol. 28 start-page: 1058 year: 2013 end-page: 1066 ident: b62 article-title: Regularization of Neural Networks using DropConnect publication-title: Proceedings of the 30th international conference on machine learning – year: 2005 ident: 10.1016/j.neunet.2018.03.019_b35 article-title: Time encoding of bandlimited signals, an overview – volume: 101 start-page: 337 issue: 1 year: 2004 ident: 10.1016/j.neunet.2018.03.019_b24 article-title: Learning rules and network repair in spike-timing-based computation networks publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.2536316100 – ident: 10.1016/j.neunet.2018.03.019_b26 – ident: 10.1016/j.neunet.2018.03.019_b3 doi: 10.1109/IJCNN.2015.7280618 – ident: 10.1016/j.neunet.2018.03.019_b2 doi: 10.1109/IJCNN.2016.7727509 – ident: 10.1016/j.neunet.2018.03.019_b9 doi: 10.1109/CVPR.2012.6248110 – volume: 78 start-page: 1 year: 2016 ident: 10.1016/j.neunet.2018.03.019_b30 article-title: Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: design methodology and selected applications publication-title: Neural Networks doi: 10.1016/j.neunet.2015.09.011 – ident: 10.1016/j.neunet.2018.03.019_b46 doi: 10.1109/IJCNN.2016.7727212 – volume: 7 start-page: e40233 issue: 8 year: 2012 ident: 10.1016/j.neunet.2018.03.019_b13 article-title: The chronotron: A neuron that learns to fire temporally precise spike patterns publication-title: PloS One doi: 10.1371/journal.pone.0040233 – year: 2018 ident: 10.1016/j.neunet.2018.03.019_b27 – volume: 52 start-page: 62 year: 2014 ident: 10.1016/j.neunet.2018.03.019_b29 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 – ident: 10.1016/j.neunet.2018.03.019_b44 doi: 10.1109/TNNLS.2018.2826721 – year: 2016 ident: 10.1016/j.neunet.2018.03.019_b39 article-title: Random synaptic feedback weights support error backpropagation for deep learning publication-title: Nature Communications doi: 10.1038/ncomms13276 – volume: 102 start-page: 652 issue: 5 year: 2014 ident: 10.1016/j.neunet.2018.03.019_b14 article-title: The SpiNNaker Project publication-title: Proceedings of the IEEE doi: 10.1109/JPROC.2014.2304638 – volume: 22 issue: 04 year: 2012 ident: 10.1016/j.neunet.2018.03.019_b43 article-title: SPAN: Spike pattern association neuron for learning spatio-temporal spike patterns publication-title: International Journal of Neural Systems doi: 10.1142/S0129065712500128 – year: 2017 ident: 10.1016/j.neunet.2018.03.019_b32 article-title: STDP-based spiking deep convolutional neural networks for object recognition publication-title: Neural Networks – volume: 10 start-page: 239 year: 2016 ident: 10.1016/j.neunet.2018.03.019_b66 article-title: Firing frequency maxima of fast-spiking neurons in human, monkey, and mouse neocortex publication-title: Frontiers in Cellular Neuroscience doi: 10.3389/fncel.2016.00239 – start-page: 41 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b60 article-title: Explicit computation of input weights in extreme learning machines – volume: 57 start-page: 345 year: 2016 ident: 10.1016/j.neunet.2018.03.019_b18 article-title: A Primer on neural network models for natural language processing publication-title: Journal of Artificial Intelligence Research (JAIR) doi: 10.1613/jair.4992 – ident: 10.1016/j.neunet.2018.03.019_b61 doi: 10.1109/IJCNN.2017.7966099 – volume: 345 start-page: 668 issue: 6197 year: 2014 ident: 10.1016/j.neunet.2018.03.019_b42 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science doi: 10.1126/science.1254642 – volume: 9 start-page: 99 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b11 article-title: Unsupervised learning of digit recognition using spike-timing-dependent plasticity publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2015.00099 – ident: 10.1016/j.neunet.2018.03.019_b52 – volume: 10 start-page: 508 year: 2016 ident: 10.1016/j.neunet.2018.03.019_b37 article-title: Training deep spiking neural networks using backpropagation publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2016.00508 – volume: 50 start-page: 303 year: 1999 ident: 10.1016/j.neunet.2018.03.019_b1 article-title: Lapicque’s introduction of the integrate-and-fire model neuron (1907) publication-title: Brain Research Bulletin doi: 10.1016/S0361-9230(99)00161-6 – start-page: 317 year: 2014 ident: 10.1016/j.neunet.2018.03.019_b16 article-title: Neuromorphic processing: A new frontier in scaling computer architecture – volume: 26 start-page: 3137 issue: 12 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b57 article-title: DL-ReSuMe: A delay learning-based remote supervised method for spiking neurons publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2015.2404938 – start-page: 149 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b34 article-title: Scalable digital CMOS Architecture for Spike based Supervised Learning – volume: 102 start-page: 699 issue: 5 year: 2014 ident: 10.1016/j.neunet.2018.03.019_b4 article-title: Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations publication-title: Proceedings of the IEEE doi: 10.1109/JPROC.2014.2313565 – ident: 10.1016/j.neunet.2018.03.019_b12 doi: 10.1109/IJCNN.2015.7280696 – volume: 18 start-page: 1527 issue: 7 year: 2006 ident: 10.1016/j.neunet.2018.03.019_b23 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation doi: 10.1162/neco.2006.18.7.1527 – volume: 192 start-page: 777 issue: 8 year: 2006 ident: 10.1016/j.neunet.2018.03.019_b55 article-title: How silent is the brain: is there a “dark matter” problem in neuroscience? publication-title: Journal of Comparative Physiology A doi: 10.1007/s00359-006-0117-6 – volume: 3 start-page: 1 issue: 2 year: 2007 ident: 10.1016/j.neunet.2018.03.019_b41 article-title: Unsupervised learning of visual features through spike timing dependent plasticity publication-title: PLOS Computational Biology doi: 10.1371/journal.pcbi.0030031 – volume: 28 start-page: 1411 issue: 6 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b67 article-title: Efficient training of supervised spiking neural network via accurate synaptic-efficiency adjustment method publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2016.2541339 – ident: 10.1016/j.neunet.2018.03.019_b45 – volume: 19 start-page: 2881 issue: 11 year: 2007 ident: 10.1016/j.neunet.2018.03.019_b6 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: 11 start-page: 682 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b53 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: 52 start-page: 925 year: 2003 ident: 10.1016/j.neunet.2018.03.019_b54 article-title: A new correlation-based measure of spike timing reliability publication-title: Neurocomputing doi: 10.1016/S0925-2312(02)00838-X – start-page: 259 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b64 article-title: SpikeComp: An evolving spiking neural network with adaptive compact structure for pattern classification – volume: 9 start-page: 222 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b56 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: 28 start-page: 30 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b65 article-title: Spiketemp: An enhanced rank-order-based learning approach for spiking neural networks with adaptive structure publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2015.2501322 – volume: 48 start-page: 17 issue: 1 year: 2002 ident: 10.1016/j.neunet.2018.03.019_b5 article-title: Error-backpropagation in temporally encoded networks of spiking neurons publication-title: Neurocomputing doi: 10.1016/S0925-2312(01)00658-0 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.neunet.2018.03.019_b36 article-title: Gradient-based learning applied to document recognition publication-title: Proceedings of the IEEE doi: 10.1109/5.726791 – ident: 10.1016/j.neunet.2018.03.019_b63 doi: 10.1109/UKRICIS.2010.5898113 – volume: 10 start-page: 333 year: 2016 ident: 10.1016/j.neunet.2018.03.019_b17 article-title: Acceleration of deep neural network training with resistive cross-point devices: Design considerations publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2016.00333 – volume: vol. 28 start-page: 1058 year: 2013 ident: 10.1016/j.neunet.2018.03.019_b62 article-title: Regularization of Neural Networks using DropConnect – volume: 10 start-page: 1659 issue: 9 year: 1997 ident: 10.1016/j.neunet.2018.03.019_b40 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: 195 start-page: 215 issue: 1 year: 1968 ident: 10.1016/j.neunet.2018.03.019_b25 article-title: Receptive fields and functional architecture of monkey striate cortex publication-title: The Journal of Physiology doi: 10.1113/jphysiol.1968.sp008455 – volume: vol. 28 start-page: 1319 year: 2013 ident: 10.1016/j.neunet.2018.03.019_b20 article-title: Maxout networks – volume: 29 start-page: 82 issue: 6 year: 2012 ident: 10.1016/j.neunet.2018.03.019_b22 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 – ident: 10.1016/j.neunet.2018.03.019_b28 doi: 10.1109/CVPR.2014.223 – volume: 8 start-page: 1 issue: 11 year: 2013 ident: 10.1016/j.neunet.2018.03.019_b68 article-title: Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns publication-title: Plos One doi: 10.1371/journal.pone.0078318 – ident: 10.1016/j.neunet.2018.03.019_b59 doi: 10.3389/fnins.2013.00153 – volume: 65 start-page: 371 year: 2005 ident: 10.1016/j.neunet.2018.03.019_b10 article-title: Energy-efficient interspike interval codes publication-title: Neurocomputing doi: 10.1016/j.neucom.2004.10.031 – volume: 113 start-page: 54 issue: 1 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b8 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 – ident: 10.1016/j.neunet.2018.03.019_b58 doi: 10.1109/FSKD.2016.7603446 – start-page: 1097 year: 2012 ident: 10.1016/j.neunet.2018.03.019_b33 article-title: ImageNet Classification with Deep Convolutional Neural Networks – ident: 10.1016/j.neunet.2018.03.019_b19 – volume: 31 start-page: 16217 issue: 45 year: 2011 ident: 10.1016/j.neunet.2018.03.019_b50 article-title: On the distribution of firing rates in networks of cortical neurons publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.1677-11.2011 – ident: 10.1016/j.neunet.2018.03.019_b7 – volume: 202 start-page: 1267 issue: 10 year: 1999 ident: 10.1016/j.neunet.2018.03.019_b15 article-title: Encoding and processing of sensory information in neuronal spike trains publication-title: Journal of Fish Biology – volume: 33 start-page: 111 issue: 3 year: 2010 ident: 10.1016/j.neunet.2018.03.019_b47 article-title: Sensory neural codes using multiplexed temporal scales publication-title: Trends in Neurosciences doi: 10.1016/j.tins.2009.12.001 – volume: 9 start-page: 420 issue: 3 year: 2006 ident: 10.1016/j.neunet.2018.03.019_b21 article-title: The tempotron: a neuron that learns spike timing-based decisions publication-title: Nature Neuroscience doi: 10.1038/nn1643 – volume: 239 start-page: 153 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b31 article-title: Population coding for neuromorphic hardware publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.02.013 – volume: 28 start-page: 900 issue: 4 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b51 article-title: An online unsupervised structural plasticity algorithm for spiking neural networks publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2016.2582517 – volume: 9 start-page: 141 year: 2015 ident: 10.1016/j.neunet.2018.03.019_b49 article-title: A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2015.00141 – volume: 28 start-page: 849 issue: 4 year: 2017 ident: 10.1016/j.neunet.2018.03.019_b38 article-title: CONE: Convex-optimized-synaptic efficacies for temporally precise spike mapping publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2015.2509479 – volume: 22 start-page: 467 issue: 2 year: 2010 ident: 10.1016/j.neunet.2018.03.019_b48 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 |
| SSID | ssj0006843 |
| Score | 2.5935333 |
| Snippet | We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 118 |
| SubjectTerms | Algorithms Approximate computing Databases, Factual - trends Handwriting Humans Learning Memory Neural networks Neural Networks (Computer) Neuromorphic computing Neurons Pattern recognition Pattern Recognition, Automated - methods Pattern Recognition, Automated - trends Spiking neurons Supervised learning Supervised Machine Learning - trends |
| Title | Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization |
| URI | https://dx.doi.org/10.1016/j.neunet.2018.03.019 https://www.ncbi.nlm.nih.gov/pubmed/29674234 https://www.proquest.com/docview/2028966838 |
| Volume | 103 |
| WOSCitedRecordID | wos000432819400012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELbYLgcuvB_lsTISt8goiZPYPi5oESBUIe2CeotSx4aUbhqlKezPZxzbaVZLtXDgElVJPEn9fRmPx-MZhF6JRNFQRQWJM5mQRCWcLJJIEBlGWoVMcdH7O75-YrMZn8_FZ1dtdNOXE2B1zS8uRPNfoYZzALbZOvsPcA9C4QT8BtDhCLDD8a-AP20q4_4OTKZK6P_axnn3aRcC4yb_1VYdGMpBWX2rumAIIFrX5HTbGM2xARt05T0mxq_uRARrUC_nbt_m2KidXX7SbnVo9cNI6R2s31v4y8FoWWmp6rK13tc3pn722P0Q8SFUFUYPqzI5EyRm_LJODelIK0ZWxV7R1tZxsHwNHQKvaOLseJ9x1irREVbNeQ9WLDKzsJzsxq4hotBfOkCHMUsFn6DD4w8n84_DqJzxhPqtk31839WHmsTQTsw-K2XfLKS3Rs7uottuGoGPLfz30A1V30d3fIkO7DT2A6QdG7BlA_YYYWADHrEB92zAf2YD9mzA0MCLwGM2PERf3p2cvX1PXGkNIsFi6Yhgkoa6ZDLWXEcpi0utRViaYj8LyeIwLhSPdCQA1rSgAr5YKZhimYwYA6Nc00doUq9r9QThQjKxoKZSPcuSVMuiZGZin8I8FEZDtZgi6rsyly7vvCl_ssp9gOEyt1jkBos8pDlgMUVkaNXYvCvX3M88SrmzHa1NmAPZrmn50oOag2o162VFrdbbDdwUc5FlnPIpemzRHt7FE-Xp3ivP0K3d9_IcTbp2q16gm_JnV23aI3TA5vzIkfQ39mmj_w |
| linkProvider | Elsevier |
| 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=Spiking+neural+networks+for+handwritten+digit+recognition-Supervised+learning+and+network+optimization&rft.jtitle=Neural+networks&rft.au=Kulkarni%2C+Shruti+R&rft.au=Rajendran%2C+Bipin&rft.date=2018-07-01&rft.eissn=1879-2782&rft.volume=103&rft.spage=118&rft_id=info:doi/10.1016%2Fj.neunet.2018.03.019&rft_id=info%3Apmid%2F29674234&rft.externalDocID=29674234 |
| 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 |