Training Spiking Neural Networks Using Lessons From Deep Learning

The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This article serves as a tutorial and perspective showing how to apply the lessons l...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE Vol. 111; no. 9; pp. 1016 - 1054
Main Authors: Eshraghian, Jason K., Ward, Max, Neftci, Emre O., Wang, Xinxin, Lenz, Gregor, Dwivedi, Girish, Bennamoun, Mohammed, Jeong, Doo Seok, Lu, Wei D.
Format: Journal Article
Language:English
Published: New York IEEE 01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Australia
Back propagation
Back propagation networks
Biological neural networks
Brain modeling
Deep learning
Distance learning
Electronic learning
neural code
Neural networks
neuromorphic
Neuromorphics
Neurons
online learning
Online tutorials
spiking neural networks (SNNs)
Synapses
Training
Tutorials
ISSN:0018-9219, 1558-2256
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This article serves as a tutorial and perspective showing how to apply the lessons learned from several decades of research in deep learning, gradient descent, backpropagation, and neuroscience to biologically plausible spiking neural networks (SNNs). We also explore the delicate interplay between encoding data as spikes and the learning process; the challenges and solutions of applying gradient-based learning to SNNs; the subtle link between temporal backpropagation and spike timing-dependent plasticity; and how deep learning might move toward biologically plausible online learning. Some ideas are well accepted and commonly used among the neuromorphic engineering community, while others are presented or justified for the first time here. A series of companion interactive tutorials complementary to this article using our Python package, snnTorch, are also made available: https://snntorch.readthedocs.io/en/latest/tutorials/index.html .
AbstractList The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This article serves as a tutorial and perspective showing how to apply the lessons learned from several decades of research in deep learning, gradient descent, backpropagation, and neuroscience to biologically plausible spiking neural networks (SNNs). We also explore the delicate interplay between encoding data as spikes and the learning process; the challenges and solutions of applying gradient-based learning to SNNs; the subtle link between temporal backpropagation and spike timing-dependent plasticity; and how deep learning might move toward biologically plausible online learning. Some ideas are well accepted and commonly used among the neuromorphic engineering community, while others are presented or justified for the first time here. A series of companion interactive tutorials complementary to this article using our Python package, snnTorch, are also made available: https://snntorch.readthedocs.io/en/latest/tutorials/index.html .
Author Jeong, Doo Seok
Dwivedi, Girish
Lenz, Gregor
Wang, Xinxin
Lu, Wei D.
Bennamoun, Mohammed
Ward, Max
Eshraghian, Jason K.
Neftci, Emre O.
Author_xml – sequence: 1
  givenname: Jason K.
  orcidid: 0000-0002-5832-4054
  surname: Eshraghian
  fullname: Eshraghian, Jason K.
  email: Jeshragh@ucsc.edu
  organization: Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
– sequence: 2
  givenname: Max
  surname: Ward
  fullname: Ward, Max
  organization: Department of Molecular and Cellular Biology, Harvard University, Cambridge, MA, USA
– sequence: 3
  givenname: Emre O.
  orcidid: 0000-0002-0332-3273
  surname: Neftci
  fullname: Neftci, Emre O.
  organization: Department of Computer Science and the Department of Cognitive Sciences, University of California at Irvine (UC Irvine), Irvine, CA, USA
– sequence: 4
  givenname: Xinxin
  orcidid: 0000-0003-0136-5936
  surname: Wang
  fullname: Wang, Xinxin
  organization: Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
– sequence: 5
  givenname: Gregor
  orcidid: 0000-0003-0619-3555
  surname: Lenz
  fullname: Lenz, Gregor
  organization: SynSense AG, Zürich, Switzerland
– sequence: 6
  givenname: Girish
  orcidid: 0000-0003-0717-740X
  surname: Dwivedi
  fullname: Dwivedi, Girish
  organization: School of Medicine, The University of Western Australia, Crawley, WA, Australia
– sequence: 7
  givenname: Mohammed
  orcidid: 0000-0002-6603-3257
  surname: Bennamoun
  fullname: Bennamoun, Mohammed
  organization: Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia
– sequence: 8
  givenname: Doo Seok
  orcidid: 0000-0001-7954-2213
  surname: Jeong
  fullname: Jeong, Doo Seok
  organization: Division of Materials Science and Engineering, Hanyang University, Seoul, South Korea
– sequence: 9
  givenname: Wei D.
  orcidid: 0000-0003-4731-1976
  surname: Lu
  fullname: Lu, Wei D.
  organization: Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
BookMark eNp9kE1LAzEQhoNUsK3-AfGw4HnrTJLdJsdSrR8UK9qeQ0wT2X5s1mSL9N-7a3sQD55eeJlnhnl6pFP60hJyiTBABHnz9PI6Gw8oUDZgDAQIcUK6mGUipTTLO6QLgCKVFOUZ6cW4AgCW5axLRvOgi7IoP5K3qli3-Wx3QW-aqL98WMdkEdt2amP0ZUwmwW-TW2urptGhBc_JqdObaC-O2SeLyd18_JBOZ_eP49E0NYxDnSLl-dAMda4z4Zh0POdINTBpnJFmicYKNHz4LpzJl8ANWu2YdQIlwpIawfrk-rC3Cv5zZ2OtVn4XyuakoiLPQILkspkShykTfIzBOmWKWteFL-vm0Y1CUK0w9SNMtcLUUViD0j9oFYqtDvv_oasDVFhrfwGUN-KRfQOX13ho
CODEN IEEPAD
CitedBy_id crossref_primary_10_1088_2634_4386_aded2d
crossref_primary_10_1103_PhysRevApplied_23_034051
crossref_primary_10_1016_j_neucom_2024_129070
crossref_primary_10_1002_admt_202401677
crossref_primary_10_1109_TCAD_2025_3543439
crossref_primary_10_1038_s41586_024_08253_8
crossref_primary_10_1126_sciadv_adt3584
crossref_primary_10_1109_TCASAI_2024_3502573
crossref_primary_10_1109_TCAD_2024_3484353
crossref_primary_10_3390_a17040156
crossref_primary_10_1088_2634_4386_ada08b
crossref_primary_10_1109_ACCESS_2025_3555539
crossref_primary_10_1109_TASC_2024_3359164
crossref_primary_10_1103_Physics_18_5
crossref_primary_10_3390_math13081361
crossref_primary_10_1002_aelm_202400835
crossref_primary_10_3389_fncom_2025_1559936
crossref_primary_10_1016_j_eng_2025_06_026
crossref_primary_10_1109_JRFID_2025_3600048
crossref_primary_10_1016_j_neunet_2024_106494
crossref_primary_10_1109_LWC_2024_3394318
crossref_primary_10_1109_TCSI_2022_3144240
crossref_primary_10_1016_j_patrec_2024_08_002
crossref_primary_10_1109_TCSI_2022_3160693
crossref_primary_10_1038_s41467_024_50490_y
crossref_primary_10_1364_OE_564050
crossref_primary_10_1146_annurev_vision_101322_104600
crossref_primary_10_3390_app14135752
crossref_primary_10_1109_TRO_2024_3508053
crossref_primary_10_1109_TNNLS_2025_3526374
crossref_primary_10_1109_TAES_2023_3334216
crossref_primary_10_1109_TCSS_2024_3420445
crossref_primary_10_1109_TCSI_2024_3387993
crossref_primary_10_1088_2632_2153_ada220
crossref_primary_10_1109_LRA_2025_3585394
crossref_primary_10_1142_S0218126625500987
crossref_primary_10_1088_2634_4386_ad8c79
crossref_primary_10_1109_ACCESS_2022_3179968
crossref_primary_10_3390_particles8020052
crossref_primary_10_1038_s41467_024_52259_9
crossref_primary_10_3389_fnins_2024_1325062
crossref_primary_10_1002_aisy_202400265
crossref_primary_10_1038_s41598_024_77779_8
crossref_primary_10_1038_s43588_024_00677_6
crossref_primary_10_1109_ACCESS_2025_3528253
crossref_primary_10_1007_s40820_025_01902_1
crossref_primary_10_1109_JSEN_2024_3487021
crossref_primary_10_3389_fcomp_2024_1447745
crossref_primary_10_1109_ACCESS_2024_3479968
crossref_primary_10_1109_TCAD_2025_3537971
crossref_primary_10_1109_TCSI_2022_3141087
crossref_primary_10_3390_s24041329
crossref_primary_10_1038_s41467_025_63493_0
crossref_primary_10_1016_j_cej_2025_167677
crossref_primary_10_1002_adfm_202423267
crossref_primary_10_1016_j_engappai_2024_109415
crossref_primary_10_3389_fnins_2024_1420119
crossref_primary_10_3390_jlpea15030050
crossref_primary_10_1016_j_nanoen_2025_111261
crossref_primary_10_3389_fnins_2024_1439414
crossref_primary_10_32604_cmc_2024_047240
crossref_primary_10_1007_s11082_025_08261_6
crossref_primary_10_1109_ACCESS_2025_3577946
crossref_primary_10_1371_journal_pcbi_1012971
crossref_primary_10_1016_j_mee_2025_112408
crossref_primary_10_1002_aelm_202300564
crossref_primary_10_1145_3730581
crossref_primary_10_1088_2634_4386_ada9a8
crossref_primary_10_1038_s41598_023_50201_5
crossref_primary_10_3390_electronics13152948
crossref_primary_10_3390_s23249781
crossref_primary_10_1109_ACCESS_2024_3462606
crossref_primary_10_3390_electronics13234665
crossref_primary_10_1109_JSEN_2024_3454153
crossref_primary_10_1109_TCAD_2024_3443000
crossref_primary_10_1587_nolta_16_222
crossref_primary_10_1007_s40998_025_00808_3
crossref_primary_10_1002_adma_202312484
crossref_primary_10_1021_acs_chemrev_4c00049
crossref_primary_10_1007_s40747_025_01845_5
crossref_primary_10_1109_TSP_2025_3592099
crossref_primary_10_3389_fninf_2024_1331220
crossref_primary_10_1016_j_orgel_2024_107144
crossref_primary_10_1016_j_knosys_2024_112037
crossref_primary_10_1016_j_neucom_2025_130423
crossref_primary_10_1038_s41377_024_01502_5
crossref_primary_10_1142_S0129065725500583
crossref_primary_10_1038_s41598_024_71678_8
crossref_primary_10_1109_JETCAS_2023_3321107
crossref_primary_10_1007_s43939_024_00077_7
crossref_primary_10_1016_j_aei_2025_103132
crossref_primary_10_1103_n41r_3t9v
crossref_primary_10_1007_s10489_024_06128_z
crossref_primary_10_1088_2634_4386_add206
crossref_primary_10_1007_s13534_024_00436_6
crossref_primary_10_3390_math12081230
crossref_primary_10_1002_adfm_202415457
crossref_primary_10_1016_j_neunet_2024_106976
crossref_primary_10_3390_electronics14183712
crossref_primary_10_1016_j_neucom_2025_130814
crossref_primary_10_1002_aelm_202500091
crossref_primary_10_1002_admt_202500786
crossref_primary_10_1088_2634_4386_addc15
crossref_primary_10_1109_JPROC_2024_3437365
crossref_primary_10_1038_s41467_025_59603_7
crossref_primary_10_1088_2634_4386_addb6c
crossref_primary_10_1109_TCSI_2025_3560666
crossref_primary_10_1038_s44335_025_00036_2
crossref_primary_10_3390_app132112068
crossref_primary_10_7498_aps_74_20250390
crossref_primary_10_1016_j_cma_2024_116847
crossref_primary_10_1109_ACCESS_2022_3187033
crossref_primary_10_1038_s41467_025_57352_1
crossref_primary_10_1002_aisy_202500351
crossref_primary_10_1109_TCSII_2024_3488526
crossref_primary_10_1109_ACCESS_2025_3588665
crossref_primary_10_1016_j_jmps_2025_106152
crossref_primary_10_1109_LRA_2025_3557744
crossref_primary_10_1109_TCSI_2022_3151920
crossref_primary_10_1109_JRFID_2022_3162952
crossref_primary_10_1109_ACCESS_2024_3425900
crossref_primary_10_1587_nolta_16_290
crossref_primary_10_1016_j_eswa_2025_126490
crossref_primary_10_1109_ACCESS_2025_3525583
crossref_primary_10_1016_j_neunet_2025_107256
crossref_primary_10_1109_TPAMI_2025_3530246
crossref_primary_10_64552_wipiec_v11i1_85
crossref_primary_10_1088_2634_4386_ad2ec3
crossref_primary_10_1002_adma_202400904
crossref_primary_10_1109_ACCESS_2022_3164440
crossref_primary_10_1109_LRA_2024_3350982
crossref_primary_10_1109_TNSRE_2025_3546682
crossref_primary_10_1017_S1759078723001575
crossref_primary_10_3390_e27040333
crossref_primary_10_1039_D3NH00421J
crossref_primary_10_3390_bioengineering12060628
crossref_primary_10_3390_electronics11244179
crossref_primary_10_3390_metabo15030174
crossref_primary_10_1364_PRJ_558405
crossref_primary_10_1007_s00371_025_04022_4
crossref_primary_10_3389_fnins_2024_1383844
crossref_primary_10_1088_2634_4386_ad5c97
crossref_primary_10_1088_2634_4386_adad0e
crossref_primary_10_1109_JPROC_2024_3429360
crossref_primary_10_1002_adma_202508803
crossref_primary_10_1016_j_micpro_2025_105187
crossref_primary_10_1109_TSG_2025_3547928
crossref_primary_10_1002_flm2_48
crossref_primary_10_3390_math12142267
crossref_primary_10_1002_aisy_202300762
crossref_primary_10_1109_JIOT_2025_3541150
crossref_primary_10_1038_s41534_024_00921_x
crossref_primary_10_1088_2634_4386_ae006c
crossref_primary_10_17308_sait_1995_5499_2024_4_156_166
crossref_primary_10_64214_jmsn_01_01005
crossref_primary_10_7717_peerj_cs_3077
crossref_primary_10_1007_s11390_024_0001_2
crossref_primary_10_1016_j_jcp_2024_113266
crossref_primary_10_1002_admt_202401587
crossref_primary_10_1109_TBCAS_2024_3456552
crossref_primary_10_1007_s13534_024_00404_0
crossref_primary_10_1109_TCDS_2024_3523338
crossref_primary_10_1007_s40747_024_01607_9
crossref_primary_10_1109_JSTSP_2024_3431996
crossref_primary_10_1109_TPEL_2024_3351911
crossref_primary_10_1038_s41377_024_01698_6
crossref_primary_10_1007_s13534_024_00405_z
crossref_primary_10_1002_smtd_202401502
crossref_primary_10_3390_app14125011
crossref_primary_10_1007_s11431_024_2762_5
crossref_primary_10_1038_s41467_023_43034_3
crossref_primary_10_1088_2634_4386_add36c
crossref_primary_10_1126_scirobotics_ads3968
crossref_primary_10_1039_D5TC01383F
crossref_primary_10_1109_JETCAS_2023_3328911
crossref_primary_10_1109_TED_2024_3442161
crossref_primary_10_1007_s00521_024_10191_5
crossref_primary_10_1016_j_jii_2025_100944
crossref_primary_10_1088_2634_4386_adc6b4
crossref_primary_10_3389_fpls_2024_1421567
crossref_primary_10_1016_j_ifacol_2024_09_050
crossref_primary_10_1021_acsami_4c21417
crossref_primary_10_1103_PhysRevB_111_014423
Cites_doi 10.1038/s41467-022-28487-2
10.3389/fnins.2015.00437
10.7551/mitpress/7503.003.0024
10.1109/TNNLS.2022.3153985
10.1523/JNEUROSCI.3508-05.2005
10.1038/323533a0
10.1109/AICAS57966.2023.10168623
10.1109/ISCAS45731.2020.9180442
10.1142/S0129065720500276
10.1016/j.neunet.2013.02.003
10.1109/ICCV.2015.169
10.3389/fnins.2018.00608
10.1007/BFb0006203
10.1109/ICCV.2019.00058
10.1016/S0896-6273(03)00761-X
10.1109/JPROC.2018.2881432
10.1126/science.275.5306.1593
10.1109/TVLSI.2018.2829918
10.1109/ISCAS.2014.6865703
10.1038/s41583-020-0277-3
10.1073/pnas.1604850113
10.1007/s00422-007-0190-0
10.1523/JNEUROSCI.18-24-10464.1998
10.3389/fnins.2021.629892
10.1109/MIM.2020.8979519
10.1109/TBCAS.2015.2479256
10.1017/CBO9781107447615
10.1016/S0896-6273(01)00542-6
10.1038/s41928-020-0436-6
10.1002/sim.2932
10.3389/fnins.2018.00774
10.1109/TNANO.2013.2250995
10.1109/JPROC.2023.3273520
10.1109/MSP.2019.2931595
10.21437/Interspeech.2010-343
10.1142/S0129065718500041
10.1145/1390156.1390177
10.3389/fnins.2020.00637
10.1109/MSPEC.2022.9729948
10.1109/ICASSP.2016.7472621
10.1126/scirobotics.abl8419
10.1038/s41586-019-1799-6
10.1109/ICASSP.2017.7953077
10.1038/nature10262
10.3389/fncom.2015.00099
10.1038/s41586-019-1724-z
10.1038/s41467-021-26022-3
10.1109/LRA.2022.3149030
10.1038/s42256-020-0219-9
10.1037/h0042519
10.1126/science.1254642
10.1038/s42256-021-00311-4
10.1016/j.cub.2015.02.036
10.1109/JPROC.2020.3045625
10.1145/3007787.3001140
10.1088/2634-4386/ace737
10.1145/3589737.3605989
10.1113/jphysiol.1962.sp006837
10.1109/JSEN.2020.3009687
10.1162/neco_a_01367
10.3389/fnins.2018.00331
10.1109/MM.2018.112130359
10.1002/aisy.201900030
10.3115/v1/D14-1179
10.1109/IJCNN.2004.1379954
10.7554/eLife.22901
10.1523/JNEUROSCI.0388-18.2018
10.1038/337129a0
10.1109/ISCAS51556.2021.9401313
10.1038/s42256-021-00315-0
10.3389/fncom.2016.00094
10.1109/JSSC.2022.3193846
10.1177/0278364917691115
10.1109/TPAMI.2013.71
10.1098/rsos.220374
10.1016/j.bspc.2020.102170
10.1016/j.apenergy.2021.116842
10.1016/j.neunet.2004.07.003
10.1038/s42003-021-01778-y
10.1016/j.neunet.2013.07.012
10.1038/s41586-019-1424-8
10.1038/s41593-019-0520-2
10.1113/jphysiol.1952.sp004764
10.1109/ICRC.2016.7738691
10.1109/TPAMI.2020.3008413
10.1109/TNNLS.2020.3044364
10.1109/TCSII.2021.3065932
10.3389/fnins.2020.00424
10.3389/fnins.2016.00563
10.1016/j.ipl.2005.05.023
10.1371/journal.pcbi.1002561
10.1109/CVPR.2019.00065
10.1109/TNNLS.2015.2404938
10.1103/RevModPhys.70.1027
10.1109/LRA.2021.3068942
10.1109/TNNLS.2014.2362542
10.3389/fnsyn.2010.00005
10.3389/fncom.2010.00024
10.1016/S0896-6273(03)00255-1
10.1007/978-1-4615-4831-7_19
10.1016/j.neuron.2018.03.044
10.1038/nature16961
10.1162/neco.2007.19.11.2881
10.1162/089976605774320539
10.18653/v1/D15-1166
10.1109/CVPR.2016.90
10.1109/CVPR.2017.781
10.1002/wcs.142
10.1109/TNN.2003.820440
10.1109/JPROC.2014.2304638
10.3389/fnins.2018.00023
10.1109/ICASSP40776.2020.9053856
10.1038/nature24636
10.1109/CVPR.2016.91
10.1109/TBCAS.2019.2953001
10.1038/nn.3382
10.1109/TBCAS.2020.3036081
10.1007/BF00336731
10.1016/j.conb.2007.07.001
10.1063/5.0162712
10.1109/JPROC.2021.3067593
10.1109/ISCAS51556.2021.9401160
10.1007/s40295-018-00140-5
10.1016/S0925-2312(01)00658-0
10.1186/1756-6606-6-10
10.1109/ICRA48506.2021.9560937
10.3389/fnins.2017.00324
10.1162/neco.1989.1.2.270
10.1038/s41586-019-1677-2
10.1038/s42256-020-0161-x
10.1109/CVPR.2014.81
10.1162/neco.1997.9.8.1735
10.1126/science.abf4588
10.1038/s41598-021-91786-z
10.1016/j.neuron.2017.05.016
10.1016/j.neunet.2004.04.004
10.3389/fnins.2017.00682
10.3389/fnins.2021.773954
10.7554/eLife.43299
10.1109/AICAS48895.2020.9073963
10.1038/s41591-018-0268-3
10.1038/s41467-020-17236-y
10.1162/neco.2009.07-07-563
10.1007/978-1-4614-6940-7_15
10.1109/JSSC.2014.2342715
10.1109/ISCAS.2016.7527296
10.1088/2634-4386/acbab8
10.1109/JSSC.2003.819169
10.1109/LRA.2018.2800793
10.1038/s42256-023-00650-4
10.3389/fnsys.2015.00151
10.1007/BF00992696
10.1109/JBHI.2022.3157877
10.1109/JETCAS.2020.3040248
10.1159/000300352
10.1038/srep27755
10.1038/nn1643
10.1016/S1383-8121(01)80015-4
10.3389/fnins.2016.00405
10.3389/fnins.2015.00481
10.1109/ICCV.2015.123
10.1016/S1364-6613(03)00055-X
10.1007/s00422-006-0068-6
10.1038/s41467-021-23342-2
10.1038/nature00807
10.1085/jgp.25.6.819
10.1007/s40747-023-00983-y
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/JPROC.2023.3308088
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2256
EndPage 1054
ExternalDocumentID 10_1109_JPROC_2023_3308088
10242251
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: ECCS-1915550
  funderid: 10.13039/100000001
GroupedDBID -DZ
-~X
.DC
0R~
123
1OL
29P
3EH
4.4
6IK
85S
97E
9M8
AAJGR
AAWTH
ABAZT
ABFSI
ABJNI
ABQJQ
ABVLG
ACBEA
ACGFS
AENEX
AETEA
AETIX
AFOGA
AGNAY
AGQYO
AGSQL
AHBIQ
AIBXA
ALLEH
ALMA_UNASSIGNED_HOLDINGS
AZLTO
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
FA8
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MVM
O9-
OCL
RIA
RIE
RIU
RNS
TAE
TN5
TWZ
UDY
UHB
UKR
UQL
VOH
WHG
XJT
XOL
YNT
ZCA
ZXP
ZY4
~02
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c340t-12467c7a6a58f39f46412a039cfc9cd1ce81c47b8fc6d04c1eaf3ef81910d2c83
IEDL.DBID RIE
ISICitedReferencesCount 313
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001066603200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9219
IngestDate Sun Sep 07 03:52:54 EDT 2025
Sat Nov 29 06:01:44 EST 2025
Tue Nov 18 22:37:17 EST 2025
Wed Aug 27 02:51:03 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 9
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c340t-12467c7a6a58f39f46412a039cfc9cd1ce81c47b8fc6d04c1eaf3ef81910d2c83
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-6603-3257
0000-0002-5832-4054
0000-0003-0717-740X
0000-0003-4731-1976
0000-0003-0136-5936
0000-0001-7954-2213
0000-0002-0332-3273
0000-0003-0619-3555
OpenAccessLink https://ieeexplore.ieee.org/document/10242251
PQID 2865090949
PQPubID 85453
PageCount 39
ParticipantIDs ieee_primary_10242251
proquest_journals_2865090949
crossref_primary_10_1109_JPROC_2023_3308088
crossref_citationtrail_10_1109_JPROC_2023_3308088
PublicationCentury 2000
PublicationDate 2023-09-01
PublicationDateYYYYMMDD 2023-09-01
PublicationDate_xml – month: 09
  year: 2023
  text: 2023-09-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle Proceedings of the IEEE
PublicationTitleAbbrev JPROC
PublicationYear 2023
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
ref207
ref56
ref208
ref59
ref205
ref206
ref53
ref203
ref55
ref201
ref54
voelker (ref82) 2019; 32
ref209
ref210
zhu (ref83) 2023
ref51
ref50
amodei (ref24) 2019
brown (ref25) 2020
laskin (ref130) 2020
williams (ref135) 1988
ref46
ref218
bengio (ref115) 2014
ref45
ref219
ref48
ref216
ref47
ref42
ref214
xiao (ref141) 2018
ref41
ref215
ref44
ref213
ref49
graves (ref7) 2014
kingma (ref179) 2014
ref8
ref9
tallec (ref194) 2018
ref3
ref6
ref5
ref100
ref221
ref101
ref222
ref40
ref220
ref35
linnainmaa (ref153) 1970
ref34
ref37
ref36
ref31
lapicque (ref75) 1907; 9
huh (ref170) 2017
ref30
ref33
glorot (ref168) 2010
ref39
renart (ref188) 2004
ref38
ref26
ref20
bellec (ref169) 2018
ref21
ref200
shrestha (ref73) 2018
olshausen (ref114) 2006; 23
ref128
ref129
ref97
ref126
ref96
ref127
ref99
ref124
ref98
ref125
fang (ref171) 2021; 34
ref93
ref133
ref92
ref95
ref131
ref94
ref132
zenke (ref150) 2019
ref91
ref90
dellaferrera (ref145) 2022
ref89
ref86
ref137
ref85
ref88
ref87
ref136
bartunov (ref140) 2018
lichtsteiner (ref65) 2006
anthony (ref27) 2020
vaswani (ref13) 2017
zhang (ref74) 2020
ref144
ref84
ref142
ref143
ref80
ref79
ref108
ref229
ref78
ref109
ref106
ref107
ref228
ref225
ref105
ref226
ref77
ref102
ref223
ref76
ref224
hebb (ref147) 1949
roth (ref196) 2018
hinton (ref212) 2016
ref71
ref232
ref70
ref112
ref230
ref110
ref231
ref119
ref67
ref117
ref69
ref118
ref64
ref236
ref63
ref116
ref66
ref113
ref234
ref235
quintana (ref202) 2023
gallego (ref68) 2019
miller (ref192) 2019
ref60
ref122
ref123
sun (ref81) 2022
ref62
ref120
ref61
ref121
modaresi (ref227) 2023
schmidgall (ref134) 2023
hu (ref158) 2018
hinton (ref146) 2022
ren (ref4) 2015; 28
godbole (ref180) 2023
ref177
ref173
ref174
ref172
amit (ref189) 1992
mujika (ref195) 2018
ref181
kag (ref204) 2021
ref186
ref187
ref184
ref185
ref182
azghadi (ref32) 2020; 2
ref183
ref149
schrimpf (ref217) 2018
p?un (ref29) 2005
ref155
ref154
ref151
ref152
duan (ref178) 2022; 35
lenz (ref104) 2021
ref159
ref157
ottati (ref175) 2023
kushnir (ref148) 2019
ref166
ref167
lillicrap (ref138) 2014
ref164
ref165
ref162
ref163
ref160
gerstner (ref72) 2001; 4
contreras (ref43) 2023
ref12
ref15
ref14
ref11
bohnstingl (ref199) 2020
hunsberger (ref156) 2015
ref17
ref16
ref19
ref18
thompson (ref23) 2020
dayan (ref58) 2001
perez-nieves (ref111) 2021
moskovitz (ref139) 2018
krizhevsky (ref1) 2012; 25
eshraghian (ref237) 2021
ioffe (ref176) 2015
paszke (ref233) 2017
rathi (ref161) 2019
ref2
mikolov (ref10) 2013
ref191
bengio (ref211) 2015
ref190
henkes (ref52) 2022
ref197
(ref22) 2023
ref193
yik (ref103) 2023
levy (ref28) 2020
marschall (ref198) 2020; 21
References_xml – year: 2014
  ident: ref138
  article-title: Random feedback weights support learning in deep neural networks
  publication-title: arXiv 1411 0247
– year: 2020
  ident: ref74
  article-title: Spike-timing-dependent back propagation in deep spiking neural networks
  publication-title: arXiv 2003 11837
– ident: ref45
  doi: 10.1038/s41467-022-28487-2
– ident: ref91
  doi: 10.3389/fnins.2015.00437
– ident: ref143
  doi: 10.7551/mitpress/7503.003.0024
– year: 2020
  ident: ref199
  article-title: Online spatio-temporal learning in deep neural networks
  publication-title: arXiv 2007 12723
– ident: ref201
  doi: 10.1109/TNNLS.2022.3153985
– year: 2020
  ident: ref27
  article-title: Carbontracker: Tracking and predicting the carbon footprint of training deep learning models
  publication-title: arXiv 2007 03051
– start-page: 1
  year: 2018
  ident: ref196
  article-title: Kernel RNN learning (keRNl)
  publication-title: Proc Int Conf Learn Represent
– ident: ref79
  doi: 10.1523/JNEUROSCI.3508-05.2005
– ident: ref152
  doi: 10.1038/323533a0
– ident: ref203
  doi: 10.1109/AICAS57966.2023.10168623
– year: 2021
  ident: ref104
  publication-title: Tonic event-based datasets and transformations
– ident: ref36
  doi: 10.1109/ISCAS45731.2020.9180442
– ident: ref120
  doi: 10.1142/S0129065720500276
– start-page: 4937
  year: 2022
  ident: ref145
  article-title: Error-driven input modulation: Solving the credit assignment problem without a backward pass
  publication-title: Proc Int Conf Mach Learn
– ident: ref164
  doi: 10.1016/j.neunet.2013.02.003
– ident: ref3
  doi: 10.1109/ICCV.2015.169
– ident: ref144
  doi: 10.3389/fnins.2018.00608
– ident: ref154
  doi: 10.1007/BFb0006203
– year: 2001
  ident: ref58
  publication-title: Theoretical Neuroscience Computational and Mathematical Modeling of Neural Systems
– ident: ref86
  doi: 10.1109/ICCV.2019.00058
– ident: ref55
  doi: 10.1016/S0896-6273(03)00761-X
– year: 2020
  ident: ref23
  article-title: The computational limits of deep learning
  publication-title: arXiv 2007 05558
– ident: ref222
  doi: 10.1109/JPROC.2018.2881432
– ident: ref122
  doi: 10.1126/science.275.5306.1593
– ident: ref66
  doi: 10.1109/TVLSI.2018.2829918
– ident: ref132
  doi: 10.1109/ISCAS.2014.6865703
– start-page: 9390
  year: 2018
  ident: ref140
  article-title: Assessing the scalability of biologically-motivated deep learning algorithms and architectures
  publication-title: Proc 32nd Int Conf Neural Inf Process Syst
– ident: ref129
  doi: 10.1038/s41583-020-0277-3
– ident: ref107
  doi: 10.1073/pnas.1604850113
– ident: ref76
  doi: 10.1007/s00422-007-0190-0
– year: 2017
  ident: ref170
  article-title: Gradient descent for spiking neural networks
  publication-title: arXiv 1706 04698
– ident: ref33
  doi: 10.1523/JNEUROSCI.18-24-10464.1998
– year: 2016
  ident: ref212
  article-title: Can the brain do back-propagation?
  publication-title: Proc Stanford Univ Colloq Comput Syst
– ident: ref142
  doi: 10.3389/fnins.2021.629892
– year: 2018
  ident: ref139
  article-title: Feedback alignment in deep convolutional networks
  publication-title: arXiv 1812 06488
– ident: ref99
  doi: 10.1109/MIM.2020.8979519
– start-page: 5189
  year: 2021
  ident: ref204
  article-title: Training recurrent neural networks via forward propagation through time
  publication-title: Proc Int Conf Mach Learn
– ident: ref41
  doi: 10.1109/TBCAS.2015.2479256
– ident: ref80
  doi: 10.1017/CBO9781107447615
– ident: ref184
  doi: 10.1016/S0896-6273(01)00542-6
– year: 2015
  ident: ref156
  article-title: Spiking deep networks with LIF neurons
  publication-title: arXiv 1510 08829
– ident: ref133
  doi: 10.1038/s41928-020-0436-6
– ident: ref116
  doi: 10.1002/sim.2932
– year: 2023
  ident: ref43
  article-title: Neuromorphic neuromodulation: Towards the next generation of on-device AI-revolution in electroceuticals
  publication-title: arXiv 2307 12471
– ident: ref162
  doi: 10.3389/fnins.2018.00774
– ident: ref210
  doi: 10.1109/TNANO.2013.2250995
– ident: ref226
  doi: 10.1109/JPROC.2023.3273520
– start-page: 448
  year: 2015
  ident: ref176
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proc Int Conf Mach Learn
– start-page: 431
  year: 2004
  ident: ref188
  article-title: Mean-field theory of irregularly spiking neuronal populations and working memory in recurrent cortical networks
  publication-title: Computational Neuroscience A Comprehensive Approach
– ident: ref172
  doi: 10.1109/MSP.2019.2931595
– ident: ref14
  doi: 10.21437/Interspeech.2010-343
– ident: ref63
  doi: 10.1142/S0129065718500041
– volume: 23
  start-page: 182
  year: 2006
  ident: ref114
  publication-title: What is the Other 85 Percent of V1 Doing
– ident: ref11
  doi: 10.1145/1390156.1390177
– ident: ref228
  doi: 10.3389/fnins.2020.00637
– start-page: 249
  year: 2010
  ident: ref168
  article-title: Understanding the difficulty of training deep feedforward neural networks
  publication-title: Proc 13th Int Conf Artif Intell Statist
– ident: ref54
  doi: 10.1109/MSPEC.2022.9729948
– ident: ref8
  doi: 10.1109/ICASSP.2016.7472621
– ident: ref44
  doi: 10.1126/scirobotics.abl8419
– ident: ref17
  doi: 10.1038/s41586-019-1799-6
– year: 2014
  ident: ref179
  article-title: Adam: A method for stochastic optimization
  publication-title: arXiv 1412 6980
– ident: ref9
  doi: 10.1109/ICASSP.2017.7953077
– year: 2019
  ident: ref192
  article-title: Stable recurrent models
  publication-title: arXiv 1805 10369
– ident: ref30
  doi: 10.1038/nature10262
– ident: ref206
  doi: 10.3389/fncom.2015.00099
– ident: ref16
  doi: 10.1038/s41586-019-1724-z
– ident: ref57
  doi: 10.1038/s41467-021-26022-3
– ident: ref46
  doi: 10.1109/LRA.2022.3149030
– year: 2019
  ident: ref68
  article-title: Event-based vision: A survey
  publication-title: arXiv 1904 08405
– volume: 25
  start-page: 1097
  year: 2012
  ident: ref1
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref26
  doi: 10.1038/s42256-020-0219-9
– ident: ref70
  doi: 10.1037/h0042519
– ident: ref220
  doi: 10.1126/science.1254642
– year: 2019
  ident: ref148
  article-title: Learning temporal structure of the input with a network of integrate-and-fire neurons
  publication-title: arXiv 1912 10262
– ident: ref160
  doi: 10.1038/s42256-021-00311-4
– ident: ref85
  doi: 10.1016/j.cub.2015.02.036
– ident: ref71
  doi: 10.1109/JPROC.2020.3045625
– ident: ref31
  doi: 10.1145/3007787.3001140
– year: 2023
  ident: ref180
  publication-title: Deep Learning Tuning Playbook Version 1 0
– volume: 32
  start-page: 1
  year: 2019
  ident: ref82
  article-title: Legendre memory units: Continuous-time representation in recurrent neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref48
  doi: 10.1088/2634-4386/ace737
– volume: 28
  start-page: 91
  year: 2015
  ident: ref4
  article-title: Faster R-CNN: Towards real-time object detection with region proposal networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref187
  doi: 10.1145/3589737.3605989
– ident: ref59
  doi: 10.1113/jphysiol.1962.sp006837
– ident: ref51
  doi: 10.1109/JSEN.2020.3009687
– ident: ref113
  doi: 10.1162/neco_a_01367
– volume: 2
  year: 2020
  ident: ref32
  article-title: Complementary metal-oxide semiconductor and memristive hardware for neuromorphic computing
  publication-title: Advances in Intelligent Systems
– ident: ref108
  doi: 10.3389/fnins.2018.00331
– year: 2021
  ident: ref237
  publication-title: snnTorch
– ident: ref219
  doi: 10.1109/MM.2018.112130359
– start-page: 1
  year: 2018
  ident: ref194
  article-title: Unbiased online recurrent optimization
  publication-title: Proc Int Conf Learn Represent
– ident: ref225
  doi: 10.1002/aisy.201900030
– ident: ref182
  doi: 10.3115/v1/D14-1179
– ident: ref185
  doi: 10.1109/IJCNN.2004.1379954
– ident: ref126
  doi: 10.7554/eLife.22901
– start-page: 1
  year: 2017
  ident: ref233
  article-title: Automatic differentiation in PyTorch
  publication-title: Proc 31st Int Conf Neural Inf Process Syst Workshop Autodiff Submission
– ident: ref216
  doi: 10.1523/JNEUROSCI.0388-18.2018
– year: 2023
  ident: ref134
  article-title: Brain-inspired learning in artificial neural networks: A review
  publication-title: arXiv 2305 11252
– year: 2020
  ident: ref130
  article-title: Parallel training of deep networks with local updates
  publication-title: arXiv 2012 03837
– ident: ref214
  doi: 10.1038/337129a0
– year: 2023
  ident: ref227
  article-title: OpenSpike: An OpenRAM SNN accelerator
  publication-title: arXiv 2302 01015
– ident: ref67
  doi: 10.1109/ISCAS51556.2021.9401313
– ident: ref34
  doi: 10.1038/s42256-021-00315-0
– ident: ref124
  doi: 10.3389/fncom.2016.00094
– ident: ref40
  doi: 10.1109/JSSC.2022.3193846
– year: 2019
  ident: ref24
  publication-title: AI and Compute
– ident: ref87
  doi: 10.1177/0278364917691115
– ident: ref155
  doi: 10.1109/TPAMI.2013.71
– ident: ref21
  doi: 10.1098/rsos.220374
– ident: ref38
  doi: 10.1016/j.bspc.2020.102170
– ident: ref53
  doi: 10.1016/j.apenergy.2021.116842
– ident: ref106
  doi: 10.1016/j.neunet.2004.07.003
– ident: ref56
  doi: 10.1038/s42003-021-01778-y
– ident: ref209
  doi: 10.1016/j.neunet.2013.07.012
– ident: ref223
  doi: 10.1038/s41586-019-1424-8
– ident: ref121
  doi: 10.1038/s41593-019-0520-2
– ident: ref77
  doi: 10.1113/jphysiol.1952.sp004764
– start-page: 2060
  year: 2006
  ident: ref65
  article-title: A 128 × 128 120 db 30 mw asynchronous vision sensor that responds to relative intensity change
  publication-title: IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers
– ident: ref157
  doi: 10.1109/ICRC.2016.7738691
– ident: ref49
  doi: 10.1109/TPAMI.2020.3008413
– ident: ref95
  doi: 10.1109/TNNLS.2020.3044364
– ident: ref131
  doi: 10.1109/TCSII.2021.3065932
– ident: ref110
  doi: 10.3389/fnins.2020.00424
– volume: 21
  start-page: 5320
  year: 2020
  ident: ref198
  article-title: A unified framework of online learning algorithms for training recurrent neural networks
  publication-title: J Mach Learn Res
– ident: ref42
  doi: 10.3389/fnins.2016.00563
– year: 2005
  ident: ref29
  publication-title: DNA Computing New Computing Paradigms
– ident: ref163
  doi: 10.1016/j.ipl.2005.05.023
– ident: ref232
  doi: 10.1371/journal.pcbi.1002561
– ident: ref173
  doi: 10.1109/CVPR.2019.00065
– year: 2018
  ident: ref158
  article-title: Spiking deep residual network
  publication-title: arXiv 1805 01352
– start-page: 6594
  year: 2018
  ident: ref195
  article-title: Approximating real-time recurrent learning with random Kronecker factors
  publication-title: Proc 32nd Int Conf Neural Inf Process Syst
– year: 2022
  ident: ref52
  article-title: Spiking neural networks for nonlinear regression
  publication-title: arXiv 2210 03515
– ident: ref186
  doi: 10.1109/TNNLS.2015.2404938
– ident: ref98
  doi: 10.1103/RevModPhys.70.1027
– ident: ref93
  doi: 10.1109/LRA.2021.3068942
– ident: ref208
  doi: 10.1109/TNNLS.2014.2362542
– ident: ref183
  doi: 10.3389/fnsyn.2010.00005
– volume: 35
  start-page: 34377
  year: 2022
  ident: ref178
  article-title: Temporal effective batch normalization in spiking neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2015
  ident: ref211
  article-title: Towards biologically plausible deep learning
  publication-title: arXiv 1502 04156
– ident: ref191
  doi: 10.3389/fncom.2010.00024
– ident: ref190
  doi: 10.1016/S0896-6273(03)00255-1
– ident: ref105
  doi: 10.1007/978-1-4615-4831-7_19
– ident: ref218
  doi: 10.1016/j.neuron.2018.03.044
– year: 2018
  ident: ref169
  article-title: Long short-term memory and learning-to-learn in networks of spiking neurons
  publication-title: arXiv 1803 09574
– ident: ref15
  doi: 10.1038/nature16961
– ident: ref207
  doi: 10.1162/neco.2007.19.11.2881
– ident: ref137
  doi: 10.1162/089976605774320539
– ident: ref12
  doi: 10.18653/v1/D15-1166
– ident: ref174
  doi: 10.1109/CVPR.2016.90
– ident: ref88
  doi: 10.1109/CVPR.2017.781
– ident: ref123
  doi: 10.1002/wcs.142
– volume: 34
  start-page: 21056
  year: 2021
  ident: ref171
  article-title: Deep residual learning in spiking neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2021
  ident: ref111
  article-title: Sparse spiking gradient descent
  publication-title: arXiv 2105 08810
– ident: ref84
  doi: 10.1109/TNN.2003.820440
– ident: ref221
  doi: 10.1109/JPROC.2014.2304638
– year: 2014
  ident: ref115
  article-title: How auto-encoders could provide credit assignment in deep networks via target propagation
  publication-title: arXiv 1407 7906
– start-page: 5998
  year: 2017
  ident: ref13
  article-title: Attention is all you need
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2018
  ident: ref217
  article-title: Brain-score: Which artificial neural network for object recognition is most brain-like?
  publication-title: BioRxiv
– ident: ref94
  doi: 10.3389/fnins.2018.00023
– ident: ref167
  doi: 10.1109/ICASSP40776.2020.9053856
– year: 2022
  ident: ref81
  article-title: Intelligence processing units accelerate neuromorphic learning
  publication-title: arXiv 2211 10725
– ident: ref235
  doi: 10.1038/nature24636
– ident: ref5
  doi: 10.1109/CVPR.2016.91
– ident: ref37
  doi: 10.1109/TBCAS.2019.2953001
– ident: ref61
  doi: 10.1038/nn.3382
– ident: ref20
  doi: 10.1109/TBCAS.2020.3036081
– ident: ref60
  doi: 10.1007/BF00336731
– ident: ref62
  doi: 10.1016/j.conb.2007.07.001
– year: 1988
  ident: ref135
  article-title: Toward a theory of reinforcement-learning connectionist systems
– ident: ref200
  doi: 10.1063/5.0162712
– ident: ref229
  doi: 10.1109/JPROC.2021.3067593
– ident: ref102
  doi: 10.1109/ISCAS51556.2021.9401160
– ident: ref50
  doi: 10.1007/s40295-018-00140-5
– ident: ref119
  doi: 10.1016/S0925-2312(01)00658-0
– ident: ref234
  doi: 10.1186/1756-6606-6-10
– ident: ref47
  doi: 10.1109/ICRA48506.2021.9560937
– ident: ref127
  doi: 10.3389/fnins.2017.00324
– ident: ref193
  doi: 10.1162/neco.1989.1.2.270
– ident: ref224
  doi: 10.1038/s41586-019-1677-2
– year: 2022
  ident: ref146
  article-title: The forward-forward algorithm: Some preliminary investigations
  publication-title: arXiv 2212 13345
– ident: ref6
  doi: 10.1038/s42256-020-0161-x
– ident: ref2
  doi: 10.1109/CVPR.2014.81
– start-page: 1764
  year: 2014
  ident: ref7
  article-title: Towards end-to-end speech recognition with recurrent neural networks
  publication-title: Proc Int Conf Mach Learn
– ident: ref181
  doi: 10.1162/neco.1997.9.8.1735
– year: 2023
  ident: ref83
  article-title: SpikeGPT: Generative pre-trained language model with spiking neural networks
  publication-title: arXiv 2302 13939
– ident: ref236
  doi: 10.1126/science.abf4588
– start-page: 3111
  year: 2013
  ident: ref10
  article-title: Distributed representations of words and phrases and their compositionality
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref166
  doi: 10.1038/s41598-021-91786-z
– ident: ref149
  doi: 10.1016/j.neuron.2017.05.016
– ident: ref128
  doi: 10.1016/j.neunet.2004.04.004
– volume: 9
  start-page: 620
  year: 1907
  ident: ref75
  article-title: Recherches quantitatives sur l'excitation electrique des nerfs traitee comme une polarization
  publication-title: J Physiol Pathol Gen
– year: 2018
  ident: ref141
  article-title: Biologically-plausible learning algorithms can scale to large datasets
  publication-title: arXiv 1811 03567
– ident: ref159
  doi: 10.3389/fnins.2017.00682
– ident: ref177
  doi: 10.3389/fnins.2021.773954
– ident: ref197
  doi: 10.7554/eLife.43299
– start-page: 6
  year: 1970
  ident: ref153
  article-title: The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors
– ident: ref100
  doi: 10.1109/AICAS48895.2020.9073963
– ident: ref18
  doi: 10.1038/s41591-018-0268-3
– start-page: 1
  year: 2019
  ident: ref161
  article-title: Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation
  publication-title: Proc Int Conf Learn Represent
– year: 2023
  ident: ref202
  article-title: ETLP: Event-based three-factor local plasticity for online learning with neuromorphic hardware
  publication-title: arXiv 2301 08281
– ident: ref109
  doi: 10.1038/s41467-020-17236-y
– ident: ref231
  doi: 10.1162/neco.2009.07-07-563
– year: 2023
  ident: ref22
  publication-title: Kaggle
– ident: ref125
  doi: 10.1007/978-1-4614-6940-7_15
– ident: ref69
  doi: 10.1109/JSSC.2014.2342715
– ident: ref35
  doi: 10.1109/ISCAS.2016.7527296
– ident: ref39
  doi: 10.1088/2634-4386/acbab8
– year: 2019
  ident: ref150
  publication-title: Spytorch
– ident: ref64
  doi: 10.1109/JSSC.2003.819169
– ident: ref90
  doi: 10.1109/LRA.2018.2800793
– ident: ref205
  doi: 10.1038/s42256-023-00650-4
– ident: ref118
  doi: 10.3389/fnsys.2015.00151
– year: 2020
  ident: ref25
  article-title: Language models are few-shot learners
  publication-title: arXiv 2005 14165
– ident: ref136
  doi: 10.1007/BF00992696
– year: 1949
  ident: ref147
  publication-title: The Organization of Behavior A Neuropsychological Theory
– ident: ref19
  doi: 10.1109/JBHI.2022.3157877
– ident: ref213
  doi: 10.1109/JETCAS.2020.3040248
– ident: ref97
  doi: 10.1159/000300352
– ident: ref215
  doi: 10.1038/srep27755
– year: 2020
  ident: ref28
  article-title: Computation in the human cerebral cortex uses less than 0.2 Watts yet this great expense is optimal when considering communication costs
  publication-title: BioRxiv
– ident: ref112
  doi: 10.1038/nn1643
– year: 1992
  ident: ref189
  publication-title: Modeling brain function The world of attractor neural networks
– volume: 4
  start-page: 469
  year: 2001
  ident: ref72
  article-title: A framework for spiking neuron models: The spike response model
  publication-title: Handbook of Biological Physics
  doi: 10.1016/S1383-8121(01)80015-4
– ident: ref89
  doi: 10.3389/fnins.2016.00405
– ident: ref92
  doi: 10.3389/fnins.2015.00481
– start-page: 1419
  year: 2018
  ident: ref73
  article-title: SLAYER: Spike layer error reassignment in time
  publication-title: Proc 32nd Int Conf Neural Inf Process Syst
– ident: ref151
  doi: 10.1109/ICCV.2015.123
– ident: ref101
  doi: 10.1016/S1364-6613(03)00055-X
– ident: ref78
  doi: 10.1007/s00422-006-0068-6
– ident: ref230
  doi: 10.1038/s41467-021-23342-2
– year: 2023
  ident: ref103
  article-title: NeuroBench: Advancing neuromorphic computing through collaborative, fair and representative benchmarking
  publication-title: arXiv 2304 04640
– ident: ref117
  doi: 10.1038/nature00807
– year: 2023
  ident: ref175
  article-title: To spike or not to spike: A digital hardware perspective on deep learning acceleration
  publication-title: arXiv 2306 15749
– ident: ref96
  doi: 10.1085/jgp.25.6.819
– ident: ref165
  doi: 10.1007/s40747-023-00983-y
SSID ssj0003563
Score 2.7529905
Snippet The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1016
SubjectTerms Australia
Back propagation
Back propagation networks
Biological neural networks
Brain modeling
Deep learning
Distance learning
Electronic learning
neural code
Neural networks
neuromorphic
Neuromorphics
Neurons
online learning
Online tutorials
spiking neural networks (SNNs)
Synapses
Training
Tutorials
Title Training Spiking Neural Networks Using Lessons From Deep Learning
URI https://ieeexplore.ieee.org/document/10242251
https://www.proquest.com/docview/2865090949
Volume 111
WOSCitedRecordID wos001066603200001&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2256
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003563
  issn: 0018-9219
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPOjBZ8VqlRy8ydakSTfJsVSLSKlFK_S2pLOJFLQtffj7TbJpLYiCtxwyS5hkZnaSme9D6Nr5RZclA0uEFiThORsmWlqbcGo9nBQd2jyAuHZEtysHA9WLzeqhF8YYE4rPTM0Pw1t-PoGlvypzFu4CSt03TG8LkRbNWmu3yxqRNo06C3Z2uOqQIer2sff81Kp5ovCaW5gkgWblOwoFWpUfvjgEmPbBP5d2iPbjnyRuFlt_hLbM-BjtbeALnqBmPxJA4JfpyN-JY4_F4YS6RfH3HIeKAdxx7s6dPtyeTT7wnTFTHGFX38rotX3fbz0kkTMhAcbJInHhOhUgdKob0jJlecppXROmwIKCnIKRFLgYSgtpTjhQoy0z1qdtJK-DZKeoNJ6MzRnCnEJKpdLMc3EIJ040gKKW5C6HAykqiK50mEEEFPe8Fu9ZSCyIyoLeM6_3LOq9gm7WMtMCTuPP2WWv6Y2ZhZIrqLraqyya3DzzLbZEuWxVnf8idoF2_deLCrEqKi1mS3OJduBzMZrPrsJp-gJw2MT5
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmqgHnxhR1B68mcV2W3bbI0EJKiJRTLhtltnWkCgQHv5-225BEqOJtx462WbamdlpZ74PoUvjF02WDCyI05gEPGP9IBVaB5xqCydF-zpzIK6tuN0WvZ7s-GZ11wujlHLFZ6pih-4tPxvB3F6VGQs3ASW0DdPrVc5DkrdrLR0vq3riNGps2FjiokeGyOv7zvNTvWKpwitmaYI4opXvOOSIVX54YxdiGrv_XNwe2vH_kriWb_4-WlPDA7S9gjB4iGpdTwGBX8YDeyuOLRqHEWrn5d9T7GoGcMs4PHP-cGMy-sA3So2xB159K6LXxm233gw8a0IAjJNZYAJ2FEOcRmlVaCY1jzgNU8IkaJCQUVCCAo_7QkOUEQ5UpZopbRM3koUg2BEqDEdDdYwwpxBRIVNm2ThiI05SAEk1yUwWByIuIbrQYQIeUtwyW7wnLrUgMnF6T6zeE6_3ErpayoxzQI0_Zxetpldm5kouofJirxJvdNPENtkSafJVefKL2AXabHYfW0nrrv1wirbsl_J6sTIqzCZzdYY24HM2mE7O3cn6At00yEA
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=Training+Spiking+Neural+Networks+Using+Lessons+From+Deep+Learning&rft.jtitle=Proceedings+of+the+IEEE&rft.au=Eshraghian%2C+Jason+K&rft.au=Ward%2C+Max&rft.au=Neftci%2C+Emre+O&rft.au=Wang%2C+Xinxin&rft.date=2023-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9219&rft.eissn=1558-2256&rft.volume=111&rft.issue=9&rft.spage=1016&rft_id=info:doi/10.1109%2FJPROC.2023.3308088&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon