Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in sp...
Gespeichert in:
| Veröffentlicht in: | Frontiers in neuroscience Jg. 14; S. 424 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Switzerland
Frontiers Research Foundation
12.05.2020
Frontiers Media S.A |
| Schlagworte: | |
| ISSN: | 1662-453X, 1662-4548, 1662-453X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using local error functions can overcome this challenge. Here, we introduce Deep Continuous Local Learning (DECOLLE), a spiking neural network equipped with local error functions for online learning with no memory overhead for computing gradients. DECOLLE is capable of learning deep spatio temporal representations from spikes relying solely on local information, making it compatible with neurobiology and neuromorphic hardware. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential. |
|---|---|
| AbstractList | A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using local error functions can overcome this challenge. Here, we introduce Deep Continuous Local Learning (DECOLLE), a spiking neural network equipped with local error functions for online learning with no memory overhead for computing gradients. DECOLLE is capable of learning deep spatio temporal representations from spikes relying solely on local information, making it compatible with neurobiology and neuromorphic hardware. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential. A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, discusses similarities between learning dynamics employed in deep Artificial Neural Network and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using locally synthesized gradients can overcome this challenge. Here, we show that synthetic gradients enable the derivation of Deep Continuous Local Learning (DECOLLE) in spiking neural networks. DECOLLE is capable of learning deep spatio-temporal representations from spikes relying solely on local information. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential. A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using local error functions can overcome this challenge. Here, we introduce Deep Continuous Local Learning (DECOLLE), a spiking neural network equipped with local error functions for online learning with no memory overhead for computing gradients. DECOLLE is capable of learning deep spatio temporal representations from spikes relying solely on local information, making it compatible with neurobiology and neuromorphic hardware. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential.A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using local error functions can overcome this challenge. Here, we introduce Deep Continuous Local Learning (DECOLLE), a spiking neural network equipped with local error functions for online learning with no memory overhead for computing gradients. DECOLLE is capable of learning deep spatio temporal representations from spikes relying solely on local information, making it compatible with neurobiology and neuromorphic hardware. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential. |
| Author | Mostafa, Hesham Kaiser, Jacques Neftci, Emre |
| AuthorAffiliation | 4 Department of Computer Science, University of California, Irvine , Irvine, CA , United States 1 FZI Research Center for Information Technology , Karlsruhe , Germany 3 Department of Cognitive Sciences, University of California, Irvine , Irvine, CA , United States 2 Department of Bioengineering, University of California, San Diego , La Jolla, CA , United States |
| AuthorAffiliation_xml | – name: 2 Department of Bioengineering, University of California, San Diego , La Jolla, CA , United States – name: 1 FZI Research Center for Information Technology , Karlsruhe , Germany – name: 4 Department of Computer Science, University of California, Irvine , Irvine, CA , United States – name: 3 Department of Cognitive Sciences, University of California, Irvine , Irvine, CA , United States |
| Author_xml | – sequence: 1 givenname: Jacques surname: Kaiser fullname: Kaiser, Jacques – sequence: 2 givenname: Hesham surname: Mostafa fullname: Mostafa, Hesham – sequence: 3 givenname: Emre surname: Neftci fullname: Neftci, Emre |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/32477050$$D View this record in MEDLINE/PubMed |
| BookMark | eNp1UstqGzEUFSWlebT7rspAN8nCjt7SbArFdlLDQAJtoTuhkTSuzFhypZmC_z6ynYYk0IW44uqco_s45-AkxOAA-IjglBBZX3fBhzzFEMMphBTTN-AMcY4nlJFfJ8_up-A85zWEHEuK34FTgqkQkMEzsPy-C3o7eFPd9zqX6IddNS-5jTe56mKq5s5tq1kMgw9jHHPVRKP7qnE6lc9X1eV8MbtrmsXVe_C20312Hx7jBfh5s_gx-zZp7m6Xs6_NxDDGhwkjBlLLueGGUamJNQgbJyhGsOOdo7KFqJYIt8IiJlrOO9t2nEODCZfMtuQCLI-6Nuq12ia_0WmnovbqkIhppXQqjfROcWtwbSVFnNXUCdfC2hFNiWmJQMS4ovXlqLUd242zxoUh6f6F6MuX4H-rVfyrBCaMUl4ELh8FUvwzujyojc_G9b0OrgxLYQolK0fUBfr5FXQdxxTKqPYoRGUtpSyoT88reirl38YKAB4BJsWck-ueIAiqvSnUwRRqbwp1MEWh8FeUsmU9-Ljvyff_Jz4Agy-7Pg |
| CitedBy_id | crossref_primary_10_1038_s41598_023_31365_6 crossref_primary_10_3389_fncom_2022_1037976 crossref_primary_10_1109_TNNLS_2022_3230914 crossref_primary_10_1016_j_cogsys_2023_101188 crossref_primary_10_3389_fnins_2024_1523331 crossref_primary_10_1007_s10044_021_01011_w crossref_primary_10_3389_fnins_2021_664208 crossref_primary_10_1016_j_neunet_2024_106415 crossref_primary_10_1038_s41598_022_11073_3 crossref_primary_10_1016_j_smhl_2021_100261 crossref_primary_10_1109_LCOMM_2021_3050207 crossref_primary_10_1088_1741_2552_ad1787 crossref_primary_10_3389_fncom_2024_1508297 crossref_primary_10_1088_2632_2153_ad8061 crossref_primary_10_1088_2634_4386_ad05da crossref_primary_10_1093_tse_tdac050 crossref_primary_10_1088_2634_4386_ac970d crossref_primary_10_3390_jcm14020550 crossref_primary_10_1088_2634_4386_ace64c crossref_primary_10_1145_3571155 crossref_primary_10_1109_TCAD_2023_3264167 crossref_primary_10_3390_make5030052 crossref_primary_10_3389_fnins_2024_1516868 crossref_primary_10_1109_TNSRE_2023_3295658 crossref_primary_10_1109_ACCESS_2023_3328220 crossref_primary_10_1016_j_neucom_2023_126234 crossref_primary_10_1002_adma_202203352 crossref_primary_10_1109_TNNLS_2022_3153985 crossref_primary_10_1109_ACCESS_2022_3179968 crossref_primary_10_1109_JPROC_2023_3308088 crossref_primary_10_1002_aisy_202400265 crossref_primary_10_1109_JETCAS_2020_3032058 crossref_primary_10_1109_TETCI_2024_3370028 crossref_primary_10_1109_TPAMI_2023_3286121 crossref_primary_10_1038_s43588_021_00184_y crossref_primary_10_1109_TSP_2021_3121632 crossref_primary_10_1016_j_chaos_2024_115060 crossref_primary_10_1109_TNNLS_2022_3144296 crossref_primary_10_3389_fnins_2022_1079357 crossref_primary_10_1016_j_patrec_2025_05_018 crossref_primary_10_1109_JETCAS_2020_3040248 crossref_primary_10_1109_TNNLS_2021_3109958 crossref_primary_10_3390_nano13243139 crossref_primary_10_1016_j_neucom_2025_131402 crossref_primary_10_1109_TVLSI_2022_3208191 crossref_primary_10_1155_2022_4242235 crossref_primary_10_1007_s11760_023_02569_0 crossref_primary_10_3390_s23249781 crossref_primary_10_3389_fnins_2023_1270090 crossref_primary_10_1038_s41928_022_00840_9 crossref_primary_10_1109_JSEN_2024_3454153 crossref_primary_10_1162_neco_a_01702 crossref_primary_10_1109_TBCAS_2022_3209073 crossref_primary_10_1016_j_neucom_2023_126773 crossref_primary_10_1063_5_0238638 crossref_primary_10_1088_2634_4386_ad3a95 crossref_primary_10_1109_ACCESS_2022_3209671 crossref_primary_10_1109_JPROC_2023_3273520 crossref_primary_10_1109_TBCAS_2024_3470520 crossref_primary_10_1038_s41598_024_78290_w crossref_primary_10_1038_s41598_021_02779_x crossref_primary_10_3389_fnins_2023_1047008 crossref_primary_10_1109_TCYB_2022_3188015 crossref_primary_10_1109_TNNLS_2021_3055421 crossref_primary_10_3390_electronics14010043 crossref_primary_10_1016_j_asoc_2025_113471 crossref_primary_10_1088_2634_4386_ada852 crossref_primary_10_1109_TPAMI_2023_3311336 crossref_primary_10_1109_TNNLS_2023_3336690 crossref_primary_10_1109_TCDS_2021_3073846 crossref_primary_10_3390_photonics9040217 crossref_primary_10_1007_s10489_024_05982_1 crossref_primary_10_1002_aisy_202400353 crossref_primary_10_1088_1674_1056_acb9f6 crossref_primary_10_1088_2634_4386_ac8828 crossref_primary_10_3389_fnins_2024_1372257 crossref_primary_10_1016_j_neunet_2025_107789 crossref_primary_10_1088_2634_4386_ac8bef crossref_primary_10_1016_j_neucom_2023_02_026 crossref_primary_10_1109_THMS_2022_3176212 crossref_primary_10_1109_ACCESS_2025_3588665 crossref_primary_10_1063_5_0162712 crossref_primary_10_3389_fnins_2021_629892 crossref_primary_10_1109_LSP_2023_3289111 crossref_primary_10_1007_s10015_022_00769_4 crossref_primary_10_1109_MM_2022_3195634 crossref_primary_10_3389_fnins_2024_1449181 crossref_primary_10_1016_j_neucom_2022_06_036 crossref_primary_10_1038_s41467_021_27653_2 crossref_primary_10_1088_2634_4386_ad2ec3 crossref_primary_10_1109_ACCESS_2025_3582564 crossref_primary_10_1088_2634_4386_ac4a83 crossref_primary_10_1088_2634_4386_ad6733 crossref_primary_10_3389_fnins_2022_760298 crossref_primary_10_1109_TNNLS_2024_3377717 crossref_primary_10_3389_fnins_2023_1107089 crossref_primary_10_1109_TCDS_2024_3396431 crossref_primary_10_1162_neco_a_01752 crossref_primary_10_1088_2634_4386_acf1c5 crossref_primary_10_3389_fnins_2022_1018006 crossref_primary_10_3389_fnins_2022_929644 crossref_primary_10_3389_fnins_2021_608567 crossref_primary_10_1063_5_0179424 crossref_primary_10_1088_2634_4386_ac5ac5 crossref_primary_10_1109_TSG_2025_3547928 crossref_primary_10_1038_s42256_023_00650_4 crossref_primary_10_1109_JPROC_2020_3045625 crossref_primary_10_1162_neco_a_01480 crossref_primary_10_1016_j_neucom_2022_11_046 crossref_primary_10_1109_TETC_2024_3440932 crossref_primary_10_1038_s41467_020_17236_y crossref_primary_10_1016_j_neunet_2025_107154 crossref_primary_10_1109_LED_2023_3347333 crossref_primary_10_1109_TCDS_2023_3308347 crossref_primary_10_1038_s41377_021_00686_4 crossref_primary_10_1109_LCOMM_2021_3050242 crossref_primary_10_1109_TCSII_2021_3098633 crossref_primary_10_1109_TNNLS_2022_3195918 crossref_primary_10_3389_fnins_2023_1266003 crossref_primary_10_1016_j_neucom_2024_128657 crossref_primary_10_1109_TBCAS_2020_3036081 crossref_primary_10_1109_JSEN_2021_3098013 crossref_primary_10_1016_j_engappai_2025_111543 crossref_primary_10_1016_j_neunet_2022_07_010 crossref_primary_10_1016_j_eswa_2025_128850 |
| Cites_doi | 10.1038/nn.2479 10.1016/j.neunet.2017.08.008 10.1162/neco_a_01086 10.3389/fnins.2016.00508 10.1038/nn1643 10.1017/CBO9780511815706 10.1007/s10827-007-0038-6 10.3389/fnins.2017.00324 10.3389/fnins.2018.00608 10.1162/NECO_a_00182 10.1016/j.neuron.2009.07.018 10.1109/JPROC.2014.2313954 10.1109/MSP.2019.2931595 10.3389/fnins.2015.00437 10.1073/pnas.1604850113 10.1109/JSSC.2007.914337 10.1126/science.1254642 10.1109/AICAS48895.2020.9073998 10.1016/j.neuron.2013.11.030 10.1162/neco.2006.18.6.1318 10.1109/TCSI.2016.2616169 10.1038/ncomms13276 10.1109/MM.2018.112130359 10.1109/5.726791 10.1162/089976602760407955 10.1162/neco.2007.19.11.2881 10.1017/CBO9781107447615 10.1162/neco.1989.1.2.270 |
| ContentType | Journal Article |
| Copyright | Copyright © 2020 Kaiser, Mostafa and Neftci. 2020. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Copyright © 2020 Kaiser, Mostafa and Neftci. 2020 Kaiser, Mostafa and Neftci |
| Copyright_xml | – notice: Copyright © 2020 Kaiser, Mostafa and Neftci. – notice: 2020. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Copyright © 2020 Kaiser, Mostafa and Neftci. 2020 Kaiser, Mostafa and Neftci |
| DBID | AAYXX CITATION NPM 3V. 7XB 88I 8FE 8FH 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO GNUQQ HCIFZ LK8 M2P M7P PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA |
| DOI | 10.3389/fnins.2020.00424 |
| DatabaseName | CrossRef PubMed ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC Biological Science Collection (subscription) ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central ProQuest Central Student SciTech Premium Collection Biological Sciences Science Database (subscription) Biological Science Database ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences Natural Science Collection ProQuest Central Korea Biological Science Collection ProQuest Central (New) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition Biological Science Database ProQuest SciTech Collection ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | PubMed Publicly Available Content Database MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Anatomy & Physiology |
| EISSN | 1662-453X |
| ExternalDocumentID | oai_doaj_org_article_6dc29d8416594e7eb09e3a43cb3713ce PMC7235446 32477050 10_3389_fnins_2020_00424 |
| Genre | Journal Article |
| GroupedDBID | --- 29H 2WC 53G 5GY 5VS 88I 8FE 8FH 9T4 AAFWJ AAYXX ABUWG ACGFO ACGFS ADRAZ AEGXH AENEX AFFHD AFKRA AFPKN AIAGR ALMA_UNASSIGNED_HOLDINGS AZQEC BBNVY BENPR BHPHI BPHCQ CCPQU CITATION CS3 DIK DU5 DWQXO E3Z EBS EJD EMOBN F5P FRP GNUQQ GROUPED_DOAJ GX1 HCIFZ HYE KQ8 LK8 M2P M48 M7P O5R O5S OK1 OVT P2P PGMZT PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC RNS RPM W2D ACXDI C1A NPM 3V. 7XB 8FK PKEHL PQEST PQUKI PRINS Q9U 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c556t-53c04d66c6c548a3dc12ce74210f6fe48b019812b7d157b66fdbf660c23685db3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 195 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000537106300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1662-453X 1662-4548 |
| IngestDate | Tue Oct 14 19:09:08 EDT 2025 Tue Nov 04 02:05:26 EST 2025 Fri Sep 05 13:35:40 EDT 2025 Fri Jul 25 11:56:36 EDT 2025 Mon Jul 21 06:06:22 EDT 2025 Sat Nov 29 02:54:51 EST 2025 Tue Nov 18 21:26:11 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | neuromorphic hardware surrogate gradient algorithm embedded learning spiking neural network backpropagataon |
| Language | English |
| License | Copyright © 2020 Kaiser, Mostafa and Neftci. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c556t-53c04d66c6c548a3dc12ce74210f6fe48b019812b7d157b66fdbf660c23685db3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 This article was submitted to Neuromorphic Engineering, a section of the journal Frontiers in Neuroscience Edited by: Kaushik Roy, Purdue University, United States Reviewed by: James Courtney Knight, University of Sussex, United Kingdom; Yulia Sandamirskaya, Intel, Germany |
| OpenAccessLink | https://doaj.org/article/6dc29d8416594e7eb09e3a43cb3713ce |
| PMID | 32477050 |
| PQID | 2401489888 |
| PQPubID | 4424402 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_6dc29d8416594e7eb09e3a43cb3713ce pubmedcentral_primary_oai_pubmedcentral_nih_gov_7235446 proquest_miscellaneous_2408540879 proquest_journals_2401489888 pubmed_primary_32477050 crossref_primary_10_3389_fnins_2020_00424 crossref_citationtrail_10_3389_fnins_2020_00424 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-05-12 |
| PublicationDateYYYYMMDD | 2020-05-12 |
| PublicationDate_xml | – month: 05 year: 2020 text: 2020-05-12 day: 12 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Lausanne |
| PublicationTitle | Frontiers in neuroscience |
| PublicationTitleAlternate | Front Neurosci |
| PublicationYear | 2020 |
| Publisher | Frontiers Research Foundation Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Research Foundation – name: Frontiers Media S.A |
| References | Eliasmith (B15) 2004 Huh (B21) 2017 Gerstner (B17) 2002 Mostafa (B35) 2017 Gerstner (B18) 2014 Sussillo (B45) 2009; 63 Bohte (B8) 2000 Bartolozzi (B3) 2006 Chicca (B11) 2013; 102 Tran (B46) 2015 Pfister (B41) 2006; 18 Gütig (B19) 2006; 9 Jaderberg (B23) 2016 Bellec (B6) 2018 Lillicrap (B31) 2014 Springenberg (B44) 2014 Williams (B48) 1989; 1 Lillicrap (B32) 2016; 7 Clopath (B12) 2010; 13 Kubilius (B27) 2019 Baldi (B2) 2017; 95 Payvand (B40) 2020 Zenke (B49) 2017 Neftci (B36) 2017; 11 Amir (B1) 2017 Lichtsteiner (B30) 2008; 43 Neftci (B38) 2019; 36 Merolla (B34) 2014; 345 Kingma (B26) 2014 Courbariaux (B13) 2016 Maass (B33) 2002; 14 Jaeger (B24) 2001 Esser (B16) 2016; 113 Neftci (B37) 2011; 23 Rastegari (B42) 2016 Shrestha (B43) 2018 Bartunov (B4) 2018 Brader (B9) 2007; 19 Orchard (B39) 2015; 9 LeCun (B28) 1998; 86 Kaiser (B25) 2018 Baydin (B5) 2017; 18 Lee (B29) 2016; 10 Urbanczik (B47) 2014; 81 Brette (B10) 2007; 23 Iyer (B22) 2018 Davies (B14) 2018; 38 Bellec (B7) 2019 Huayaney (B20) 2016; 63 |
| References_xml | – volume: 13 start-page: 344 year: 2010 ident: B12 article-title: Connectivity reflects coding: a model of voltage-based STDP with homeostasis publication-title: Nat. Neurosci doi: 10.1038/nn.2479 – volume: 95 start-page: 110 year: 2017 ident: B2 article-title: Learning in the machine: the symmetries of the deep learning channel publication-title: Neural Netw doi: 10.1016/j.neunet.2017.08.008 – year: 2017 ident: B49 article-title: Superspike: Supervised learning in multi-layer spiking neural networks publication-title: arXiv [Preprint]. arXiv:1705.11146 doi: 10.1162/neco_a_01086 – volume: 10 start-page: 508 year: 2016 ident: B29 article-title: Training deep spiking neural networks using backpropagation publication-title: Front. Neurosci doi: 10.3389/fnins.2016.00508 – start-page: 525 volume-title: European Conference on Computer Vision year: 2016 ident: B42 article-title: “Xnor-net: Imagenet classification using binary convolutional neural networks,” – year: 2018 ident: B25 article-title: Synaptic plasticity for deep continuous local learning publication-title: arXiv [Preprint]. arXiv:1812.10766 – volume: 9 start-page: 420 year: 2006 ident: B19 article-title: The tempotron: a neuron that learns spike timing-based decisions publication-title: Nat. Neurosci doi: 10.1038/nn1643 – start-page: 1 volume-title: Brain Inspired Cognitive Systems, BICS 2006 year: 2006 ident: B3 article-title: “Silicon synaptic homeostasis,” – year: 2002 ident: B17 publication-title: Spiking Neuron Models. Single Neurons, Populations, Plasticity doi: 10.1017/CBO9780511815706 – volume: 23 start-page: 349 year: 2007 ident: B10 article-title: Simulation of networks of spiking neurons: a review of tools and strategies publication-title: J. Comput. Neurosci doi: 10.1007/s10827-007-0038-6 – year: 2004 ident: B15 publication-title: Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems – volume: 11 start-page: 324 year: 2017 ident: B36 article-title: Event-driven random back-propagation: Enabling neuromorphic deep learning machines publication-title: Front. Neurosci doi: 10.3389/fnins.2017.00324 – year: 2014 ident: B44 article-title: Striving for simplicity: the all convolutional net publication-title: arXiv [Preprint]. arXiv:1412.6806 – year: 2017 ident: B35 article-title: Deep supervised learning using local errors publication-title: arXiv [Preprint]. arXiv:1711.06756 doi: 10.3389/fnins.2018.00608 – volume: 23 start-page: 2457 year: 2011 ident: B37 article-title: A systematic method for configuring VLSI networks of spiking neurons publication-title: Neural Comput doi: 10.1162/NECO_a_00182 – volume: 63 start-page: 544 year: 2009 ident: B45 article-title: Generating coherent patterns of activity from chaotic neural networks publication-title: Neuron doi: 10.1016/j.neuron.2009.07.018 – year: 2018 ident: B6 article-title: Long short-term memory and learning-to-learn in networks of spiking neurons publication-title: arXiv [Preprint]. arXiv:1803.09574 – volume: 102 start-page: 1367 year: 2013 ident: B11 article-title: Neuromorphic electronic circuits for building autonomous cognitive systems publication-title: Proc. IEEE doi: 10.1109/JPROC.2014.2313954 – volume: 36 start-page: 51 year: 2019 ident: B38 article-title: Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks publication-title: IEEE Signal Process. Mag doi: 10.1109/MSP.2019.2931595 – year: 2001 ident: B24 publication-title: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note – volume: 9 start-page: 437 year: 2015 ident: B39 article-title: Converting static image datasets to spiking neuromorphic datasets using saccades publication-title: Front. Neurosci doi: 10.3389/fnins.2015.00437 – start-page: 9368 volume-title: Advances in Neural Information Processing Systems year: 2018 ident: B4 article-title: “Assessing the scalability of biologically-motivated deep learning algorithms and architectures,” – volume: 113 start-page: 11441 year: 2016 ident: B16 article-title: Convolutional networks for fast, energy-efficient neuromorphic computing publication-title: Proc. Natl. Acad. Sci. U.S.A doi: 10.1073/pnas.1604850113 – volume: 43 start-page: 566 year: 2008 ident: B30 article-title: An 128x128 120dB 15μs-latency temporal contrast vision sensor publication-title: IEEE J. Solid State Circuits doi: 10.1109/JSSC.2007.914337 – start-page: 1412 volume-title: Advances in Neural Information Processing Systems year: 2018 ident: B43 article-title: “Slayer: Spike layer error reassignment in time,” – volume: 345 start-page: 668 year: 2014 ident: B34 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science doi: 10.1126/science.1254642 – volume-title: 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) year: 2020 ident: B40 article-title: “Error-triggered three-factor learning dynamics for crossbar arrays,” doi: 10.1109/AICAS48895.2020.9073998 – start-page: 4489 volume-title: Proceedings of the IEEE International Conference on Computer Vision year: 2015 ident: B46 article-title: “Learning spatiotemporal features with 3D convolutional networks,” – volume: 81 start-page: 521 year: 2014 ident: B47 article-title: Learning by the dendritic prediction of somatic spiking publication-title: Neuron doi: 10.1016/j.neuron.2013.11.030 – year: 2018 ident: B22 article-title: Is neuromorphic mnist neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain publication-title: arXiv [Preprint]. arXiv:1807.01013 – volume: 18 start-page: 1318 year: 2006 ident: B41 article-title: Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning publication-title: Neural Comput doi: 10.1162/neco.2006.18.6.1318 – volume: 63 start-page: 2189 year: 2016 ident: B20 article-title: Learning in silicon beyond STDP: a neuromorphic implementation of multi-factor synaptic plasticity with calcium-based dynamics publication-title: IEEE Trans. Circuits Syst. I doi: 10.1109/TCSI.2016.2616169 – year: 2016 ident: B13 article-title: Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1 publication-title: arXiv [Preprint]. arXiv:1602.02830 – volume: 7 start-page: 13276 year: 2016 ident: B32 article-title: Random synaptic feedback weights support error backpropagation for deep learning publication-title: Nat. Commun doi: 10.1038/ncomms13276 – volume: 38 start-page: 82 year: 2018 ident: B14 article-title: Loihi: a neuromorphic manycore processor with on-chip learning publication-title: IEEE Micro doi: 10.1109/MM.2018.112130359 – start-page: 419 volume-title: ESANN year: 2000 ident: B8 article-title: “Spikeprop: backpropagation for networks of spiking neurons,” – year: 2019 ident: B7 article-title: Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets publication-title: arXiv [Preprint]. arXiv:1901.09049 – volume: 86 start-page: 2278 year: 1998 ident: B28 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – volume: 18 start-page: 5595 year: 2017 ident: B5 article-title: Automatic differentiation in machine learning: a survey publication-title: J. Mach. Learn. Res – volume: 14 start-page: 2531 year: 2002 ident: B33 article-title: Real-time computing without stable states: a new framework for neural computation based on perturbations publication-title: Neural Comput doi: 10.1162/089976602760407955 – year: 2014 ident: B26 article-title: Adam: A method for stochastic optimization publication-title: arXiv Preprint. arXiv:1412.6980 – start-page: 7243 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2017 ident: B1 article-title: “A low power, fully event-based gesture recognition system,” – volume: 19 start-page: 2881 year: 2007 ident: B9 article-title: Learning real world stimuli in a neural network with spike-driven synaptic dynamics publication-title: Neural Comput doi: 10.1162/neco.2007.19.11.2881 – year: 2019 ident: B27 article-title: Brain-like object recognition with high-performing shallow recurrent ANNs publication-title: arXiv [Preprint]. arXiv:1909.06161 – year: 2014 ident: B31 article-title: Random feedback weights support learning in deep neural networks publication-title: arXiv [Preprint]. arXiv:1411.0247 – year: 2014 ident: B18 publication-title: Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition doi: 10.1017/CBO9781107447615 – volume: 1 start-page: 270 year: 1989 ident: B48 article-title: A learning algorithm for continually running fully recurrent neural networks publication-title: Neural Comput doi: 10.1162/neco.1989.1.2.270 – year: 2016 ident: B23 article-title: Decoupled neural interfaces using synthetic gradients publication-title: arXiv [Preprint]. arXiv:1608.05343 – year: 2017 ident: B21 article-title: Gradient descent for spiking neural networks publication-title: arXiv [Preprint]. arXiv:1706.04698 |
| SSID | ssj0062842 |
| Score | 2.6502807 |
| Snippet | A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 424 |
| SubjectTerms | Back propagation backpropagataon Computers Deep learning embedded learning Firing pattern Learning algorithms Machine learning Neural networks neuromorphic hardware Neurons Neuroplasticity Neuroscience Propagation spiking neural network surrogate gradient algorithm Synaptic plasticity |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELagy4ELr4XdwIKMhBB7iOokjh2f0O62K5CqUvGQ9hYlfiyVWLf0gdR_z4zjVhShvXDIJXEUx2PPfOMZf0PIG-Y0Z7YSqSkNxyM5PFWOmxTMTSutqACUV6HYhByPq6srNYkbbsuYVrnViUFRm5nGPfI-WB5A7goctvfznylWjcLoaiyhcZccIFMZ75GD8-F48nmriwUo3xDvFHg2CMB5F6gEt0z1nZ965OvOMbeL53zPMAX-_n-Bzr9zJ_8wRpcP__c3HpEHEYbSs27ePCZ3rH9CDs88uOA3G_qWhsTQsON-SD5-2fgGNIumE4DamIW92tBBV8l-SQH00oG1c4o8V1O_nq2XdIQGkkbq1mv6bjC8-DQaDU-fkm-Xw68XH9JYgSHVZSlWaVloxo0QWmgYvKYwOsu1BW86Y044y6sWECJAhFaarJStEM60Tgimc-S1N23xjPT8zNtjQmGyFEwDntGN5cq4SkvXNko0mcsk0zwh_e3w1zrSk2OVjB81uCkosDoIrEaB1UFgCTndvTHvqDluaXuOEt21Q1LtcGO2uK7jGq2F0bkyGIctFbfStkzZouGFbgtw5bVNyMlWpnVc6fCNnUAT8nr3GNYoBl4ab2HU60AjB5dUCTnqps-uJwBopWQlS4jcm1h7Xd1_4qffAw-4zIsSvPnnt3frBbmP44AZD1l-Qnqrxdq-JPf0r9V0uXgVF8xvycsesA priority: 102 providerName: ProQuest |
| Title | Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE) |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/32477050 https://www.proquest.com/docview/2401489888 https://www.proquest.com/docview/2408540879 https://pubmed.ncbi.nlm.nih.gov/PMC7235446 https://doaj.org/article/6dc29d8416594e7eb09e3a43cb3713ce |
| Volume | 14 |
| WOSCitedRecordID | wos000537106300001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: DOA dateStart: 20070101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1662-453X dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M7P dateStart: 20071015 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1662-453X dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: BENPR dateStart: 20071015 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1662-453X dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: PIMPY dateStart: 20071015 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (subscription) customDbUrl: eissn: 1662-453X dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M2P dateStart: 20071015 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB5By4ELAsojUFZGQogeojqJY8fHtrsVlbZLxENaTlHiB6wEpmq3SPvvmXGyqy5CcOEQH_JQnPFjvs-efAPwinsjuKtkaksr6JcckWovbIruplNOVgjKq5hsQs1m1Xyu6xupvigmrJcH7g13KK3JtaXNsVILp1zHtStaUZiuQH5lHM2-iHrWZKqfgyVOunm_KYkUTB_6sAikzZ1THJfIxZYTilr9fwKYv8dJ3nA8p_fh3oAY2VFf0wdwy4WHsHcUkC1_X7HXLMZwxsXxPTj7sAotTgKG1YiKKWB6uWLjPun8FUN8ysbOXTCSpFqEayT9bEq-jA0qq1_Ym_Hk5N10Ojl4BJ9OJx9P3qZDsoTUlKVcpmVhuLBSGmmQhLSFNVluHBLfjHvpnag6BHPozTtls1J1UnrbeSm5yUmC3nbFY9gJP4J7CgzbteAGoYdpndDWV0b5rtWyzXymuBEJHK6t15hBSZwSWnxrkFGQvZto74bs3UR7J3CweeKiV9H4y73H1CCb-0j_Op7AXtEMvaL5V69IYH_dnM0wKPEdgpZPNXL-BF5uLuNwoj2SNji0ehMV3_BQOoEnfetvaoLYUyle8gTUVr_Yqur2lbD4GiW7VV6USLyf_Y9vew53yVoUwpDl-7CzvLx2L-CO-blcXF2O4LaaVyPYPZ7M6vejOCqwPM9rKhWWu_XZef35F8SlE4c |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VggQXXuVhKLBIgOjBih_rXfuAUGlSNaoJkShSb669uy6RqB3yAOVP8RuZ2dgWQai3HjjkYjvOZv3tzDee2W8AXnml4p6JhasjzWlLDneTkmsX3U0hjYiRlMe22YQcjeLT02S8Bb_avTBUVtnaRGuoda3oHXkPPQ8y9wQDtvfT7y51jaLsattCYw2LY7P6iSHb_N2wj8_3dRAcDk4Ojtymq4Crokgs3ChUHtdCKKGQreehVn6gDEaIvleK0vC4QNaDbq-Q2o9kIUSpi1IITwWk1a6LEO97Da4jjQhiWyo4bi2_QFNvs6uCdiLhzddpUQwCk15ZTSpSBw-okowHfMMN2m4B_6K4f1dq_uH6Du_8b5N2F243JJvtr1fFPdgy1X3Y2a_yRX2xYm-YLXu1-YQdGH5eVTnaTcXGGEhQjflixfp47GKi5gwpPesbM2Wk4jWplvVyzlJy_6wRpj1nb_uDg09pOth7AF-u5E89hO2qrsxjYLgUQk8hW1O54YkuYyXLIk9E7pe-9BR3oNc-7kw14uvUA-RbhkEYASSzAMkIIJkFiAN73Tema-GRS679QAjqriPJcHugnp1njQXKhFZBoinLHCXcSFN4iQlzHqoilH6ojAO7LYayxo7hb3QAcuBldxotEKWV8srgrGdWJA8_MnHg0Rqu3UiQrkvpRZ4DcgPIG0PdPFNNvlqVcxmEEefiyeXDegE3j04-plk6HB0_hVs0J1Tb4Qe7sL2YLc0zuKF-LCbz2XO7VBmcXTXMfwMonXlx |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VghAXXuVhKLBIgOjBih_rXfuAUGkSETUKkQCpN2Pvo43UOiFxQPlr_DpmNnZEEOqtBw6-2Ov1ev3tzDee2RmAV4FVPDCp8HWiOW3J4X5mufZR3ZTSiBRJeeqKTcjRKD05ycY78KvdC0Nhla1MdIJaTxX9I--g5kHmnpHBZpuwiHG3_3723acKUuRpbctprCFybFY_0XxbvBt08Vu_jqJ-78vRR7-pMOCrJBG1n8Qq4FoIJRQy9yLWKoyUQWsxDKywhqclMiBUgaXUYSJLIawurRCBiihvuy5j7PcaXJcce6OwwWjcagGBYt95WgXtSsLO1y5SNAizjq0mFWUKjyiqjEd8SyW6ygH_ort_R23-oQb7d_7nCbwLtxvyzQ7Xq-Ue7JjqPuwdVkU9vVixN8yFwzo_wx4MPq-qAuWpYmM0MCj2vF6xLp67mKgFQ6rPusbMGGX3mlTL6XLBhkQLWJOw9pS97faOPg2HvYMH8PVKXuoh7FbTyjwGhkskDhSyOFUYnmmbKmnLIhNFaEMZKO5Bp_30uWqSslNtkPMcjTMCS-7AkhNYcgcWDw42d8zWCUkuafuB0LRpR6nE3Ynp_DRvJFMutIoyTd7nJONGmjLITFzwWJWxDGNlPNhv8ZQ38g2fsQGTBy83l1EykbupqAzOeu6S5-EhMw8eraG7GQnSeCmDJPBAboF6a6jbV6rJmct-LqM44Vw8uXxYL-AmojsfDkbHT-EWTQmFfITRPuzW86V5BjfUj3qymD93q5bBt6tG-W8y6oIt |
| 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=Synaptic+Plasticity+Dynamics+for+Deep+Continuous+Local+Learning+%28DECOLLE%29&rft.jtitle=Frontiers+in+neuroscience&rft.au=Kaiser%2C+Jacques&rft.au=Mostafa%2C+Hesham&rft.au=Neftci%2C+Emre&rft.date=2020-05-12&rft.pub=Frontiers+Media+S.A&rft.issn=1662-4548&rft.eissn=1662-453X&rft.volume=14&rft_id=info:doi/10.3389%2Ffnins.2020.00424&rft_id=info%3Apmid%2F32477050&rft.externalDocID=PMC7235446 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1662-453X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1662-453X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1662-453X&client=summon |