Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network

This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (S...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Neural networks Ročník 134; s. 64 - 75
Hlavní autoři:	Demin, V.A., Nekhaev, D.V., Surazhevsky, I.A., Nikiruy, K.E., Emelyanov, A.V., Nikolaev, S.N., Rylkov, V.V., Kovalchuk, M.V.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States Elsevier Ltd 01.02.2021
Témata:	Algorithms Hardware analog neuron Memristive STDP Memristor Models, Neurological Neural Networks, Computer Neuronal Plasticity - physiology Neurons - physiology Pattern Recognition, Automated - methods Probabilistic generative model Spiking neural network Unsupervised learning Hardware analog neuron Memristor Memristive STDP Probabilistic generative model Spiking neural network Unsupervised learning
ISSN:	0893-6080, 1879-2782, 1879-2782
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)x(LiNbO3)1−x nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of “correlation growth-anticorrelation decay” principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain. •Supporting correlations in activities of neurons is a near-optimal learning policy.•Binary clusterization can be a benchmark for tuning parameters of a rate-coding SNN.•Shaping memristive STDP window for binary clusterization helps in more complex tasks.•Nanocomposite LiNbO3-based memristors are suitable for always-on learning SNNs.
AbstractList	This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)x(LiNbO3)1-x nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of "correlation growth-anticorrelation decay" principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain.This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)x(LiNbO3)1-x nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of "correlation growth-anticorrelation decay" principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain. This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)x(LiNbO3)1−x nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of “correlation growth-anticorrelation decay” principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain. •Supporting correlations in activities of neurons is a near-optimal learning policy.•Binary clusterization can be a benchmark for tuning parameters of a rate-coding SNN.•Shaping memristive STDP window for binary clusterization helps in more complex tasks.•Nanocomposite LiNbO3-based memristors are suitable for always-on learning SNNs. This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB) (LiNbO ) nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of "correlation growth-anticorrelation decay" principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain.
Author	Surazhevsky, I.A. Nikiruy, K.E. Kovalchuk, M.V. Emelyanov, A.V. Rylkov, V.V. Nikolaev, S.N. Nekhaev, D.V. Demin, V.A.
Author_xml	– sequence: 1 givenname: V.A. orcidid: 0000-0001-9142-4295 surname: Demin fullname: Demin, V.A. email: demin_va@nrcki.ru organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 2 givenname: D.V. surname: Nekhaev fullname: Nekhaev, D.V. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 3 givenname: I.A. surname: Surazhevsky fullname: Surazhevsky, I.A. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 4 givenname: K.E. surname: Nikiruy fullname: Nikiruy, K.E. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 5 givenname: A.V. surname: Emelyanov fullname: Emelyanov, A.V. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 6 givenname: S.N. surname: Nikolaev fullname: Nikolaev, S.N. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 7 givenname: V.V. surname: Rylkov fullname: Rylkov, V.V. organization: National Research Center “Kurchatov Institute”, Moscow, Russia – sequence: 8 givenname: M.V. surname: Kovalchuk fullname: Kovalchuk, M.V. organization: National Research Center “Kurchatov Institute”, Moscow, Russia
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33291017$$D View this record in MEDLINE/PubMed
BookMark	eNqFkUtrHDEQhEVwiNdO_kEIOuYyaz1mNBofDMHxI2CSgH0XevQsWs9Ia0lr438fbda--JCcGpqviu6qI3QQYgCEPlOypISKk_UywDZAWTLC6oouCeneoQWV_dCwXrIDtCBy4I0gkhyio5zXhBAhW_4BHXLOhmrSL9DqJ1jIWadnbGNwvvgYMh5jwrd33383RmdweKNLgRRwAhtX4S-DJ9Ap-LDCPmCNZ5iTz8U_As4bf7_b1-uSnuooTzHdf0TvRz1l-PQyj9Ht5cXd-XVz8-vqx_m3m8ZywUrDtWAgBkv6kQ2uda4z1DhOwcBIOTEd1dS1lnTSGKqF6TQxUgoBhvRa8GP0de-6SfFhC7mo2WcL06QDxG1WrBVS9DWWrqJfXtCtmcGpTfJzTUG9RlOB0z1gU8w5waisL3r3e0naT4oStetBrdW-B7XrQVGqag9V3L4Rv_r_R3a2l0GN6NFDUtl6CBacr9kX5aL_t8EfrNql_w
CitedBy_id	crossref_primary_10_3389_fncom_2022_859874 crossref_primary_10_1016_j_jallcom_2021_160760 crossref_primary_10_3390_biomimetics8030277 crossref_primary_10_1016_j_chaos_2021_110783 crossref_primary_10_3367_UFNe_2021_05_038978 crossref_primary_10_1038_s41598_021_96197_8 crossref_primary_10_1088_1361_6463_ac203c crossref_primary_10_1007_s12668_025_02024_z crossref_primary_10_1007_s11063_023_11312_2 crossref_primary_10_3367_UFNr_2021_05_038978 crossref_primary_10_1016_j_jmst_2021_04_071 crossref_primary_10_1134_S2635167623700180 crossref_primary_10_1016_j_neucom_2023_126682 crossref_primary_10_1016_j_apsusc_2021_150563 crossref_primary_10_1016_j_mejo_2024_106449 crossref_primary_10_1016_j_aeue_2022_154424 crossref_primary_10_1007_s11571_025_10234_0 crossref_primary_10_3390_math11183888 crossref_primary_10_3390_s21082730 crossref_primary_10_1016_j_chaos_2024_115959 crossref_primary_10_1134_S2635167621020154 crossref_primary_10_1002_aelm_202200215 crossref_primary_10_1016_j_tsf_2023_139842 crossref_primary_10_1088_1361_6463_ac79de crossref_primary_10_3390_nano12193455 crossref_primary_10_1016_j_apsusc_2021_152164 crossref_primary_10_1016_j_nanoen_2024_109272 crossref_primary_10_1134_S1063785021070075 crossref_primary_10_1016_j_aei_2024_102408 crossref_primary_10_3103_S0027134924702400 crossref_primary_10_1155_2023_5220356 crossref_primary_10_3390_bdcc7040184 crossref_primary_10_3390_math9243237 crossref_primary_10_1109_TCSI_2025_3553058 crossref_primary_10_1002_pssb_202200150 crossref_primary_10_1109_TNNLS_2023_3335450 crossref_primary_10_1134_S2635167621060057 crossref_primary_10_3103_S0027134924702084 crossref_primary_10_1134_S2635167623601067 crossref_primary_10_1002_pssr_202100471 crossref_primary_10_1134_S1064226923100170 crossref_primary_10_1007_s00521_023_09135_2 crossref_primary_10_1039_D5NR00456J crossref_primary_10_1109_TCSI_2023_3250699 crossref_primary_10_1016_j_jallcom_2022_164743 crossref_primary_10_1016_j_neunet_2022_05_031 crossref_primary_10_1155_2022_5883324 crossref_primary_10_32604_cmc_2024_051860 crossref_primary_10_1016_j_neunet_2022_11_023 crossref_primary_10_1088_2634_4386_ad5c97 crossref_primary_10_3390_bdcc8030022 crossref_primary_10_1007_s00521_022_07170_z crossref_primary_10_1134_S263516762106015X crossref_primary_10_1134_S263516762460250X crossref_primary_10_1134_S2635167623601535 crossref_primary_10_1002_aisy_202100151 crossref_primary_10_1002_aisy_202200407 crossref_primary_10_3390_s21165587 crossref_primary_10_1109_JEDS_2025_3556675 crossref_primary_10_1134_S2635167621060161 crossref_primary_10_1016_j_neunet_2025_107564 crossref_primary_10_1088_2634_4386_ac734a crossref_primary_10_64214_jmsn_01_01005 crossref_primary_10_1016_j_chaos_2024_114648 crossref_primary_10_1016_j_flatc_2024_100755 crossref_primary_10_1016_j_neunet_2024_106355 crossref_primary_10_3390_jlpea12010014 crossref_primary_10_3390_biomimetics10080514 crossref_primary_10_1016_j_chaos_2021_111540 crossref_primary_10_1002_acs_3831 crossref_primary_10_1109_TKDE_2022_3178176 crossref_primary_10_3389_fnins_2022_983950 crossref_primary_10_1007_s00521_022_07513_w crossref_primary_10_1109_ACCESS_2024_3412109 crossref_primary_10_1016_j_chaos_2021_111223 crossref_primary_10_1016_j_neunet_2023_07_031 crossref_primary_10_1134_S2635167621060227 crossref_primary_10_3390_sym15020535 crossref_primary_10_1016_j_neucom_2024_127448 crossref_primary_10_3390_met12081370 crossref_primary_10_1016_j_amc_2025_129715
Cites_doi	10.1073/pnas.1105933108 10.3389/fnins.2013.00002 10.1523/JNEUROSCI.18-24-10464.1998 10.1038/s41928-018-0023-2 10.1134/S1063776118020152 10.1021/acs.nanolett.5b00697 10.1021/acs.nanolett.7b00552 10.1038/s42256-018-0001-4 10.3389/fnins.2020.00088 10.1126/science.1254642 10.3389/fnins.2014.00412 10.1021/nl904092h 10.1162/neco.2007.19.6.1437 10.1109/MM.2018.112130359 10.1109/TNANO.2013.2250995 10.1038/nmat3510 10.3389/fnins.2016.00056 10.1109/TETCI.2018.2829922 10.1088/1361-6528/ab4a6d 10.1103/PhysRevLett.86.364 10.3389/fnins.2016.00482 10.1038/srep21331 10.1021/acsami.7b11191 10.1038/s41928-019-0270-x 10.1038/nature06932 10.1038/s41928-017-0002-z 10.1109/JSSC.2018.2884901 10.1109/JPROC.2014.2304638 10.1016/j.neunet.2019.09.004 10.1038/s41563-019-0291-x 10.1088/1361-6463/aad361 10.1007/s00422-008-0233-1 10.1111/j.2517-6161.1977.tb01600.x 10.1134/S1064226919100103 10.1073/pnas.1815682116 10.1162/089976603321891783 10.1134/S1063785019040278 10.1162/NECO_a_00446 10.1063/1.4963830 10.1109/IJCNN.2017.7966072 10.1146/annurev.neuro.31.060407.125639 10.1523/JNEUROSCI.20-23-08812.2000 10.1134/S106378501805022X 10.1016/j.neunet.2019.10.013 10.1038/s41598-019-47263-9 10.1007/s00521-020-04755-4 10.1063/1.5142089 10.1146/annurev-neuro-072116-031005 10.3389/fninf.2018.00079
ContentType	Journal Article
Copyright	2020 Elsevier Ltd Copyright © 2020 Elsevier Ltd. All rights reserved.
Copyright_xml	– notice: 2020 Elsevier Ltd – notice: Copyright © 2020 Elsevier Ltd. All rights reserved.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1016/j.neunet.2020.11.005
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 - Academic MEDLINE
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	75
ExternalDocumentID	33291017 10_1016_j_neunet_2020_11_005 S0893608020303907
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 CGR CUY CVF ECM EIF NPM PKN 7X8
ID	FETCH-LOGICAL-c362t-3a62e69c07f29d4dd5b1bd31ebef130b51a1d4c058bb1a6b5a0b8866eb07a63
ISICitedReferencesCount	97
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000603296800006&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	Wed Oct 01 14:00:51 EDT 2025 Wed Feb 19 02:29:14 EST 2025 Sat Nov 29 07:09:33 EST 2025 Tue Nov 18 22:40:11 EST 2025 Fri Feb 23 02:48:28 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Hardware analog neuron Memristor Memristive STDP Probabilistic generative model Spiking neural network Unsupervised learning
Language	English
License	Copyright © 2020 Elsevier Ltd. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c362t-3a62e69c07f29d4dd5b1bd31ebef130b51a1d4c058bb1a6b5a0b8866eb07a63
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0001-9142-4295
PMID	33291017
PQID	2468670895
PQPubID	23479
PageCount	12
ParticipantIDs	proquest_miscellaneous_2468670895 pubmed_primary_33291017 crossref_citationtrail_10_1016_j_neunet_2020_11_005 crossref_primary_10_1016_j_neunet_2020_11_005 elsevier_sciencedirect_doi_10_1016_j_neunet_2020_11_005
PublicationCentury	2000
PublicationDate	February 2021 2021-02-00 2021-Feb 20210201
PublicationDateYYYYMMDD	2021-02-01
PublicationDate_xml	– month: 02 year: 2021 text: February 2021
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Neural networks
PublicationTitleAlternate	Neural Netw
PublicationYear	2021
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Gerstner, Kistler (b22) 2002 Hebb (b27) 1949 Chen, Kumar, Sumbul, Knag, Krishnamurthy (b9) 2019; 54 Covi, George, Frascaroli, Brivio, Mayr, Mostafa (b13) 2018; 51 Demin, Nekhaev (b16) 2018; 12 Querlioz, Bichler, Dollfus, Gamrat (b60) 2013; 12 Morrison, Aertsen, Diesmann (b47) 2007; 19 Prezioso, Merrikh-Bayat, Hoskins, Likharev, Strukov (b58) 2016; 6 Mikhaylov, Morozov, Ovchinnikov, Antonov, Belov, Korolev (b44) 2018; 2 Ielmini, Waser (b29) 2016 Bi, Poo (b4) 1998; 18 Habenschuss, Bill, Nessler (b25) 2012 (pp. 1823–1830). Furber, Galluppi, Temple, Plana (b21) 2014; 102 Moraitis, T., Sebastian, A., Boybat, I., Le Gallo, M., Tuma, T., & Eleftheriou, E. (2017). Fatiguing STDP: Learning from spike-timing codes in the presence of rate codes. B: In Rubin, Lee, Sompolinsky (b63) 2001; 86 Bill, Legenstein (b5) 2014; 8 Kim, Kim, Hwang, Kim, Chang, Park (b34) 2017; 9 Martyshov, Emelyanov, Demin, Nikiruy, Minnekhanov, Nikolaev (b41) 2020; 14 Choi, Shin, Lee, Sheridan, Lu (b11) 2017; 17 Rossi (b61) 2018 Mahalanabis, Sivaraj, Chen, Shah, Barnaby, Kozicki (b39) 2016 Merolla, Arthur, Alvarez-Icaza, Cassidy, Sawada, Akopyan (b42) 2014; 345 Boyn, Grollier, Lecerf, Xu, Locatelli, Fusil (b6) 2017; 8 Kim, Du, Sheridan, Ma, Choi, Lu (b33) 2015; 15 Wang, Li, Song, Rao, Belkin, Li (b71) 2019 Chicca, Indiveri (b10) 2020; 116 Dempster, Laird, Rubin (b17) 1977; 39 Li, Hu, Li, Jiang, Ge, Montgomery (b35) 2018; 1 Wang, Joshi, Savel’ev, Song, Midya, Li (b70) 2018; 1 Morrison, Diesmann, Gerstner (b48) 2008; 98 Emelyanov, Nikiruy, Serenko, Sitnikov, Presnyakov, Rybka (b20) 2020; 31 Habenschuss, Puhr, Maass (b26) 2013; 25 Serb, Bill, Khiat, Berdan, Legenstein, Prodromakis (b65) 2016; 7 Dowling, Slipko, Pershin (b18) 2020 Nikiruy, Emelyanov, Rylkov, Sitnikov, Presnyakov, Kukueva (b53) 2019; 64 Cai, Correll, Lee, Lim, Bothra, Zhang (b7) 2019; 2 Strukov, Snider, Stewart, Williams (b68) 2008; 453 Sun, Pedretti, Ambrosi, Bricalli, Wang, Ielmini (b69) 2019; 116 Qu, Zhao, Wang, Wang (b59) 2020 Merrikh-Bayat, Prezioso, Chakrabarti, Nili, Kataeva, Strukov (b43) 2018; 9 Nikiruy, Emelyanov, Rylkov, Sitnikov, Demin (b52) 2019; 45 Nikiruy, Emelyanov, Demin, Sitnikov, Minnekhanov, Rylkov (b51) 2019; 9 Prezioso, Mahmoodi, Merrikh-Bayat, Nili, Kim, Vincent (b57) 2018; 9 Serrano-Gotarredona, Masquelier, Prodromakis, Indiveri, Linares-Barranco (b66) 2013; 7 Davies, Srinivasa, Lin, Chinya, Cao, Choday (b14) 2018; 38 Minnekhanov, Emelyanov, Lapkin, Nikiruy, Shvetsov, Nesmelov (b45) 2019; 9 Lobo, Del Ser, Bifet, Kasabov (b37) 2020; 121 Nikiruy, Surazhevsky, Demin, Emelyanov (b54) 2020 Del Valle, Ramírez, Rozenberg, Schuller (b15) 2018; 124 Silva, Sanz, Seixas, Solano, Omar (b67) 2020; 122 Rossum, Bi, Turrigiano (b62) 2000; 20 Emelyanov, Lapkin, Demin, Erokhin, Battistoni, Baldi (b19) 2016; 6 Glazman, Matveev (b24) 1988; 67 Izhikevich, Desai (b30) 2003; 15 Hennequin, Agnes, Vogels (b28) 2017; 40 Rylkov, Nikolaev, Demin, Emelyanov, Sitnikov, Nikiruy (b64) 2018; 126 Acciarito, Cardarilli, Cristini, Nunzio, Fazzolari, Khanal (b1) 2017; 59 Nessler, Pfeiffer, Maass (b49) 2009 Akhmetov, James (b2) 2019 Caporale, Dan (b8) 2008; 31 Maier, Hartmann, Rebello Sousa Dias, Emmerling, Schneider, Castelano (b40) 2016; 120 Li, Wang, Rao, Belkin, Song, Jiang (b36) 2019; 1 Covi, Brivio, Serb, Prodromakis, Fanciulli, Spiga (b12) 2016; 10 Jo, Chang, Ebong, Bhadviya, Mazumder, Lu (b31) 2010; 10 Pfister, Gerstner (b55) 2005; 1 Lobov, Mikhaylov, Shamshin, Makarov, Kazantsev (b38) 2020; 14 Xia, Yang (b73) 2019; 18 Nikiruy, Emelyanov, Demin, Rylkov, Sitnikov, Kashkarov (b50) 2018; 44 Ambrogio, Ciocchini, Laudato, Milo, Pirovano, Fantini (b3) 2016; 10 Gjorgjieva, Clopath, Audet, Pfister (b23) 2011; 108 Wu, Saxena, Zhu (b72) 2015 Keskar, Nocedal, Tang, Mudigere, Smelyanskiy (b32) 2016 Pickett, Medeiros-Ribeiro, Williams (b56) 2013; 12 Boyn (10.1016/j.neunet.2020.11.005_b6) 2017; 8 Covi (10.1016/j.neunet.2020.11.005_b12) 2016; 10 Merolla (10.1016/j.neunet.2020.11.005_b42) 2014; 345 Gerstner (10.1016/j.neunet.2020.11.005_b22) 2002 Acciarito (10.1016/j.neunet.2020.11.005_b1) 2017; 59 Bill (10.1016/j.neunet.2020.11.005_b5) 2014; 8 Rossum (10.1016/j.neunet.2020.11.005_b62) 2000; 20 Li (10.1016/j.neunet.2020.11.005_b36) 2019; 1 Serrano-Gotarredona (10.1016/j.neunet.2020.11.005_b66) 2013; 7 Chen (10.1016/j.neunet.2020.11.005_b9) 2019; 54 Kim (10.1016/j.neunet.2020.11.005_b33) 2015; 15 Nessler (10.1016/j.neunet.2020.11.005_b49) 2009 Del Valle (10.1016/j.neunet.2020.11.005_b15) 2018; 124 Nikiruy (10.1016/j.neunet.2020.11.005_b50) 2018; 44 Ielmini (10.1016/j.neunet.2020.11.005_b29) 2016 Rubin (10.1016/j.neunet.2020.11.005_b63) 2001; 86 Furber (10.1016/j.neunet.2020.11.005_b21) 2014; 102 Choi (10.1016/j.neunet.2020.11.005_b11) 2017; 17 Wu (10.1016/j.neunet.2020.11.005_b72) 2015 Hebb (10.1016/j.neunet.2020.11.005_b27) 1949 Gjorgjieva (10.1016/j.neunet.2020.11.005_b23) 2011; 108 Kim (10.1016/j.neunet.2020.11.005_b34) 2017; 9 Cai (10.1016/j.neunet.2020.11.005_b7) 2019; 2 Serb (10.1016/j.neunet.2020.11.005_b65) 2016; 7 Izhikevich (10.1016/j.neunet.2020.11.005_b30) 2003; 15 Lobov (10.1016/j.neunet.2020.11.005_b38) 2020; 14 Prezioso (10.1016/j.neunet.2020.11.005_b57) 2018; 9 Lobo (10.1016/j.neunet.2020.11.005_b37) 2020; 121 Minnekhanov (10.1016/j.neunet.2020.11.005_b45) 2019; 9 Rossi (10.1016/j.neunet.2020.11.005_b61) 2018 Chicca (10.1016/j.neunet.2020.11.005_b10) 2020; 116 10.1016/j.neunet.2020.11.005_b46 Habenschuss (10.1016/j.neunet.2020.11.005_b25) 2012 Pickett (10.1016/j.neunet.2020.11.005_b56) 2013; 12 Akhmetov (10.1016/j.neunet.2020.11.005_b2) 2019 Dowling (10.1016/j.neunet.2020.11.005_b18) 2020 Pfister (10.1016/j.neunet.2020.11.005_b55) 2005; 1 Strukov (10.1016/j.neunet.2020.11.005_b68) 2008; 453 Qu (10.1016/j.neunet.2020.11.005_b59) 2020 Emelyanov (10.1016/j.neunet.2020.11.005_b19) 2016; 6 Nikiruy (10.1016/j.neunet.2020.11.005_b51) 2019; 9 Morrison (10.1016/j.neunet.2020.11.005_b48) 2008; 98 Xia (10.1016/j.neunet.2020.11.005_b73) 2019; 18 Mahalanabis (10.1016/j.neunet.2020.11.005_b39) 2016 Maier (10.1016/j.neunet.2020.11.005_b40) 2016; 120 Keskar (10.1016/j.neunet.2020.11.005_b32) 2016 Mikhaylov (10.1016/j.neunet.2020.11.005_b44) 2018; 2 Wang (10.1016/j.neunet.2020.11.005_b71) 2019 Covi (10.1016/j.neunet.2020.11.005_b13) 2018; 51 Jo (10.1016/j.neunet.2020.11.005_b31) 2010; 10 Martyshov (10.1016/j.neunet.2020.11.005_b41) 2020; 14 Sun (10.1016/j.neunet.2020.11.005_b69) 2019; 116 Nikiruy (10.1016/j.neunet.2020.11.005_b53) 2019; 64 Prezioso (10.1016/j.neunet.2020.11.005_b58) 2016; 6 Habenschuss (10.1016/j.neunet.2020.11.005_b26) 2013; 25 Li (10.1016/j.neunet.2020.11.005_b35) 2018; 1 Emelyanov (10.1016/j.neunet.2020.11.005_b20) 2020; 31 Davies (10.1016/j.neunet.2020.11.005_b14) 2018; 38 Ambrogio (10.1016/j.neunet.2020.11.005_b3) 2016; 10 Merrikh-Bayat (10.1016/j.neunet.2020.11.005_b43) 2018; 9 Nikiruy (10.1016/j.neunet.2020.11.005_b52) 2019; 45 Silva (10.1016/j.neunet.2020.11.005_b67) 2020; 122 Dempster (10.1016/j.neunet.2020.11.005_b17) 1977; 39 Nikiruy (10.1016/j.neunet.2020.11.005_b54) 2020 Querlioz (10.1016/j.neunet.2020.11.005_b60) 2013; 12 Rylkov (10.1016/j.neunet.2020.11.005_b64) 2018; 126 Bi (10.1016/j.neunet.2020.11.005_b4) 1998; 18 Glazman (10.1016/j.neunet.2020.11.005_b24) 1988; 67 Caporale (10.1016/j.neunet.2020.11.005_b8) 2008; 31 Morrison (10.1016/j.neunet.2020.11.005_b47) 2007; 19 Demin (10.1016/j.neunet.2020.11.005_b16) 2018; 12 Hennequin (10.1016/j.neunet.2020.11.005_b28) 2017; 40 Wang (10.1016/j.neunet.2020.11.005_b70) 2018; 1
References_xml	– volume: 19 start-page: 1437 year: 2007 end-page: 1467 ident: b47 article-title: Spike-timing-dependent plasticity in balanced random networks publication-title: Neural Computation – volume: 59 start-page: 81 year: 2017 end-page: 89 ident: b1 article-title: Hardware design of LIF with Latency neuron model with memristive STDP synapses publication-title: IEEE Transactions on Very Large Scale Integration (VLSI) Systems – volume: 86 start-page: 364 year: 2001 end-page: 367 ident: b63 article-title: Equilibrium properties of temporally asymmetric Hebbian plasticity publication-title: Physical Review Letters – volume: 18 start-page: 10464 year: 1998 end-page: 10472 ident: b4 article-title: Synaptic modifications in cultured hippocampal neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic cell type publication-title: The Journal of Neuroscience – volume: 122 start-page: 273 year: 2020 end-page: 278 ident: b67 article-title: Perceptrons from memristors publication-title: Neural Networks – volume: 7 start-page: 12611 year: 2016 ident: b65 article-title: Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses publication-title: Neural Computation – volume: 102 start-page: 652 year: 2014 end-page: 665 ident: b21 article-title: The SpiNNaker project publication-title: Proceedings of the IEEE – volume: 9 year: 2019 ident: b51 article-title: Dopamine-like STDP modulation in nanocomposite memristors publication-title: Advances – volume: 9 start-page: 40420 year: 2017 end-page: 40427 ident: b34 article-title: Analog synaptic behavior of a Silicon Nitride Memristor publication-title: ACS Applied Materials & Interfaces – volume: 18 start-page: 309 year: 2019 end-page: 323 ident: b73 article-title: Memristive crossbar arrays for brain-inspired computing publication-title: Nature Materials – year: 2020 ident: b54 article-title: Spike-timing-dependent and spike-shape-independent plasticities with dopamine-like modulation in nanocomposite memristive synapses publication-title: Physica Status Solidi (A) Applications and Materials Science – volume: 6 start-page: 21331 year: 2016 ident: b58 article-title: Self-adaptive Spike-Time-Dependent Plasticity of Metal-oxide memristors publication-title: Scientific Reports – volume: 40 start-page: 557 year: 2017 end-page: 579 ident: b28 article-title: Inhibitory plasticity: Balance, control, and codependence publication-title: Annual Review of Neuroscience – volume: 108 start-page: 19383 year: 2011 end-page: 19388 ident: b23 article-title: A triplet spike-timing-dependent plasticity model generalizes the Bienenstock-Cooper-Munro rule to higher-order spatiotemporal correlations publication-title: Proceedings of the National Academy of Sciences of the United States of America – start-page: 1 year: 2015 end-page: 6 ident: b72 article-title: A CMOS spiking neuron for Dense memristor-synapse connectivity for brain-inspired computing publication-title: B: Int. Jt. Conf. Neural Networks 2015 – volume: 31 year: 2020 ident: b20 article-title: Self-adaptive STDP-based learning of a spiking neuron with nanocomposite memristive weights publication-title: Nanotechnology – volume: 8 start-page: 14736 year: 2017 ident: b6 article-title: Learning through ferroelectric domain dynamics in solid-state synapses publication-title: Neural Computation – volume: 15 start-page: 1511 year: 2003 end-page: 1523 ident: b30 article-title: Relating STDP to BCM publication-title: Neural Computation – year: 2016 ident: b32 article-title: On large-batch training for deep learning: Generalization gap and sharp minima – year: 2016 ident: b29 article-title: Resistive switching: From fundamentals of nanoionic redox processes to memristive device applications – volume: 64 start-page: 1035 year: 2019 end-page: 1039 ident: b53 article-title: Formation of a memristive array of crossbar-structures based on (Co40Fe40B20)x(LiNbO3)100-x Nanocomposite publication-title: Journal of Communications Technology and Electronics – volume: 8 start-page: 412 year: 2014 ident: b5 article-title: A compound memristive synapse model for statistical learning through STDP in spiking neural networks publication-title: Frontiers in Neuroscience – volume: 67 start-page: 1276 year: 1988 end-page: 1282 ident: b24 article-title: Inelastic tunneling across thin amorphous films publication-title: Soviet Physics - JETP – volume: 6 year: 2016 ident: b19 article-title: First steps towards the realization of a double layer perceptron based on organic memristive devices publication-title: Advances – volume: 51 start-page: 34003 year: 2018 ident: b13 article-title: Spike-driven threshold-based learning with memristive synapses and neuromorphic silicon neurons publication-title: Journal of Physics D (Applied Physics) – volume: 9 start-page: 10800 year: 2019 ident: b45 article-title: Parylene Based Memristive Devices with Multilevel resistive switching for Neuromorphic applications publication-title: Scientific Reports – volume: 12 start-page: 288 year: 2013 end-page: 295 ident: b60 article-title: Immunity to device variations in a spiking neural network with memristive nanodevices publication-title: IEEE Transactions on Nanotechnology – reference: Moraitis, T., Sebastian, A., Boybat, I., Le Gallo, M., Tuma, T., & Eleftheriou, E. (2017). Fatiguing STDP: Learning from spike-timing codes in the presence of rate codes. B: In – start-page: 773 year: 2012 end-page: 781 ident: b25 article-title: Homeostatic plasticity in Bayesian spiking networks a Expectation Maximization with posterior constraints publication-title: Advances in Neural Information Processing Systems – year: 2002 ident: b22 article-title: Spiking neuron models – volume: 25 start-page: 1 year: 2013 end-page: 37 ident: b26 article-title: Emergence of optimal decoding of population codes through STDP publication-title: Neural Computation – volume: 2 start-page: 371 year: 2018 end-page: 379 ident: b44 article-title: One-board design and simulation of double-layer perceptron based on metal-oxide memristive nanostructures publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence – volume: 38 start-page: 82 year: 2018 end-page: 99 ident: b14 article-title: Loihi: A neuromorphic Manycore processor with On-Chip Learning publication-title: IEEE Micro – volume: 14 year: 2020 ident: b41 article-title: Multifilamentary character of anticorrelated capacitive and resistive switching in memristive structures based on (CoFeB)x(LiNbO3)100-x nanocomposite publication-title: Physical Review A – year: 2019 ident: b2 article-title: Probabilistic neural network with memristive crossbar circuits publication-title: Proc - IEEE Int Symp Circuits Syst – volume: 14 start-page: 88 year: 2020 ident: b38 article-title: Spatial properties of STDP in a self-learning spiking neural network enable controlling a mobile robot publication-title: Frontiers in Neuroscience – volume: 12 start-page: 79 year: 2018 ident: b16 article-title: Recurrent spiking neural network learning based on a competitive maximization of neuronal activity publication-title: Frontiers in Neuroinformatics – volume: 10 start-page: 1297 year: 2010 end-page: 1301 ident: b31 article-title: Nanoscale memristor device as synapse in neuromorphic systems publication-title: Nano Letters – volume: 1 start-page: 52 year: 2018 end-page: 59 ident: b35 article-title: Analogue signal and image processing with large memristor crossbars publication-title: Nature Electronics – volume: 31 start-page: 25 year: 2008 end-page: 46 ident: b8 article-title: Spike timing–dependent Plasticity: A Hebbian learning rule publication-title: Annual Review of Neuroscience – volume: 20 start-page: 8812 year: 2000 end-page: 8821 ident: b62 article-title: Stable Hebbian learning from spike timing-dependent plasticity publication-title: The Journal of Neuroscience – year: 1949 ident: b27 article-title: The organization of behavior – volume: 98 start-page: 459 year: 2008 end-page: 478 ident: b48 article-title: Phenomenological models of synaptic plasticity based on spike timing publication-title: Biological Cybernetics – volume: 15 start-page: 2203 year: 2015 end-page: 2211 ident: b33 article-title: Experimental demonstration of a second-order memristor and its ability to biorealistically implement synaptic plasticity publication-title: Nano Letters – volume: 45 start-page: 386 year: 2019 end-page: 390 ident: b52 article-title: Adaptive properties of spiking neuromorphic networks with synapses based on memristive elements publication-title: Technical Physics Letters – volume: 1 start-page: 137 year: 2018 end-page: 145 ident: b70 article-title: Fully memristive neural networks for pattern classification with unsupervised learning publication-title: Nature Electronics – volume: 1 start-page: 49 year: 2019 end-page: 57 ident: b36 article-title: Long short-term memory networks in memristor crossbar arrays publication-title: Nature Machine Intelligence – volume: 12 start-page: 114 year: 2013 end-page: 117 ident: b56 article-title: A scalable neuristor built with Mott memristors publication-title: Nature Materials – volume: 124 year: 2018 ident: b15 article-title: Challenges in materials and devices for resistive-switching-based neuromorphic computing publication-title: Journal of Applied Physics – volume: 126 start-page: 424 year: 2018 end-page: 441 ident: b64 article-title: Transport, magnetic, and memristive properties of a nanogranular (CoFeB)x(LiNbOy)100 – x Composite Material publication-title: Journal of Experimental and Theoretical Physics – year: 2018 ident: b61 article-title: Mathematical statistics: An introduction to likelihood based inference – volume: 54 start-page: 992 year: 2019 end-page: 1002 ident: b9 article-title: A 4096-Neuron 1M-Synapse 3.8-pJ/SOP spiking neural network with On-Chip STDP Learning and Sparse Weights in 10-nm FinFET CMOS publication-title: IEEE Journal of Solid-State Circuits – reference: (pp. 1823–1830). – volume: 116 year: 2020 ident: b10 article-title: A recipe for creating ideal hybrid memristive-CMOS neuromorphic processing systems publication-title: Applied Physics Letters – volume: 17 start-page: 3113 year: 2017 end-page: 3118 ident: b11 article-title: Experimental demonstration of feature extraction and dimensionality reduction using memristor networks publication-title: Nano Letters – volume: 9 start-page: 2331 year: 2018 ident: b43 article-title: Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits publication-title: Neural Computation – volume: 453 start-page: 80 year: 2008 end-page: 83 ident: b68 article-title: The missing memristor found publication-title: Nature – year: 2020 ident: b59 article-title: Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks publication-title: Neural Computing and Applications – volume: 39 start-page: 1 year: 1977 end-page: 38 ident: b17 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: The Journal of the Royal Statistical Society, Series B – volume: 44 start-page: 416 year: 2018 end-page: 419 ident: b50 article-title: A precise algorithm of memristor switching to a state with preset resistance publication-title: Technical Physics Letters – start-page: 1357 year: 2009 end-page: 1365 ident: b49 article-title: STDP enables spiking neurons to detect hidden causes of their inputs publication-title: Adv Neural Inf Process Syst 22 - Proc 2009 Conf – volume: 1 start-page: 1081 year: 2005 end-page: 1088 ident: b55 article-title: Beyond pair-based STDP: A phenomenogical rule for spike triplet and frequency effects publication-title: Advances in Neural Information Processing Systems – year: 2020 ident: b18 article-title: Probabilistic Memristive networks: Application of a Master Equation to Networks of binary ReRAM cells – volume: 7 start-page: 2 year: 2013 ident: b66 article-title: STDP and STDP variations with memristors for spiking neuromorphic learning systems publication-title: Frontiers in Neuroscience – volume: 10 start-page: 56 year: 2016 ident: b3 article-title: Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM) synapses publication-title: Frontiers in Neuroscience – volume: 10 start-page: 482 year: 2016 ident: b12 article-title: Analog memristive synapse in spiking networks implementing unsupervised learning publication-title: Frontiers in Neuroscience – volume: 120 year: 2016 ident: b40 article-title: Mimicking of pulse shape-dependent learning rules with a quantum dot memristor publication-title: Journal of Applied Physics – 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 (80- ) – year: 2019 ident: b71 article-title: Reinforcement learning with analogue memristor arrays publication-title: Nature Electronics – volume: 2 start-page: 290 year: 2019 end-page: 299 ident: b7 article-title: A fully integrated reprogrammable memristor–CMOS system for efficient multiply–accumulate operations publication-title: Nature Electronics – start-page: 2314 year: 2016 end-page: 2317 ident: b39 article-title: Demonstration of spike timing dependent plasticity in CBRAM devices with silicon neurons publication-title: B: Proc. - IEEE Int. Symp. Circuits Syst. – volume: 9 start-page: 5311 year: 2018 ident: b57 article-title: Spike-timing-dependent plasticity learning of coincidence detection with passively integrated memristive circuits publication-title: Neural Computation – volume: 121 start-page: 88 year: 2020 end-page: 100 ident: b37 article-title: Spiking Neural Networks and online learning: An overview and perspectives publication-title: Neural Networks – volume: 116 start-page: 4123 year: 2019 end-page: 4128 ident: b69 article-title: Solving matrix equations in one step with cross-point resistive arrays publication-title: Proceedings of the National Academy of Sciences of the United States of America – volume: 108 start-page: 19383 issue: 48 year: 2011 ident: 10.1016/j.neunet.2020.11.005_b23 article-title: A triplet spike-timing-dependent plasticity model generalizes the Bienenstock-Cooper-Munro rule to higher-order spatiotemporal correlations publication-title: Proceedings of the National Academy of Sciences of the United States of America doi: 10.1073/pnas.1105933108 – volume: 7 start-page: 2 year: 2013 ident: 10.1016/j.neunet.2020.11.005_b66 article-title: STDP and STDP variations with memristors for spiking neuromorphic learning systems publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2013.00002 – volume: 9 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b51 article-title: Dopamine-like STDP modulation in nanocomposite memristors publication-title: Advances – volume: 18 start-page: 10464 issue: 24 year: 1998 ident: 10.1016/j.neunet.2020.11.005_b4 article-title: Synaptic modifications in cultured hippocampal neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic cell type publication-title: The Journal of Neuroscience doi: 10.1523/JNEUROSCI.18-24-10464.1998 – volume: 1 start-page: 137 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b70 article-title: Fully memristive neural networks for pattern classification with unsupervised learning publication-title: Nature Electronics doi: 10.1038/s41928-018-0023-2 – volume: 6 issue: 11 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b19 article-title: First steps towards the realization of a double layer perceptron based on organic memristive devices publication-title: Advances – volume: 124 issue: 21 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b15 article-title: Challenges in materials and devices for resistive-switching-based neuromorphic computing publication-title: Journal of Applied Physics – volume: 126 start-page: 424 issue: 3 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b64 article-title: Transport, magnetic, and memristive properties of a nanogranular (CoFeB)x(LiNbOy)100 – x Composite Material publication-title: Journal of Experimental and Theoretical Physics doi: 10.1134/S1063776118020152 – volume: 15 start-page: 2203 year: 2015 ident: 10.1016/j.neunet.2020.11.005_b33 article-title: Experimental demonstration of a second-order memristor and its ability to biorealistically implement synaptic plasticity publication-title: Nano Letters doi: 10.1021/acs.nanolett.5b00697 – volume: 17 start-page: 3113 year: 2017 ident: 10.1016/j.neunet.2020.11.005_b11 article-title: Experimental demonstration of feature extraction and dimensionality reduction using memristor networks publication-title: Nano Letters doi: 10.1021/acs.nanolett.7b00552 – start-page: 773 year: 2012 ident: 10.1016/j.neunet.2020.11.005_b25 article-title: Homeostatic plasticity in Bayesian spiking networks a Expectation Maximization with posterior constraints publication-title: Advances in Neural Information Processing Systems – volume: 1 start-page: 49 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b36 article-title: Long short-term memory networks in memristor crossbar arrays publication-title: Nature Machine Intelligence doi: 10.1038/s42256-018-0001-4 – year: 2016 ident: 10.1016/j.neunet.2020.11.005_b29 – year: 2020 ident: 10.1016/j.neunet.2020.11.005_b18 – volume: 14 start-page: 88 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b38 article-title: Spatial properties of STDP in a self-learning spiking neural network enable controlling a mobile robot publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2020.00088 – volume: 345 start-page: 668 issue: 6197 year: 2014 ident: 10.1016/j.neunet.2020.11.005_b42 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science (80- ) doi: 10.1126/science.1254642 – volume: 1 start-page: 1081 year: 2005 ident: 10.1016/j.neunet.2020.11.005_b55 article-title: Beyond pair-based STDP: A phenomenogical rule for spike triplet and frequency effects publication-title: Advances in Neural Information Processing Systems – volume: 8 start-page: 412 year: 2014 ident: 10.1016/j.neunet.2020.11.005_b5 article-title: A compound memristive synapse model for statistical learning through STDP in spiking neural networks publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2014.00412 – volume: 8 start-page: 14736 year: 2017 ident: 10.1016/j.neunet.2020.11.005_b6 article-title: Learning through ferroelectric domain dynamics in solid-state synapses publication-title: Neural Computation – volume: 10 start-page: 1297 year: 2010 ident: 10.1016/j.neunet.2020.11.005_b31 article-title: Nanoscale memristor device as synapse in neuromorphic systems publication-title: Nano Letters doi: 10.1021/nl904092h – volume: 19 start-page: 1437 issue: 6 year: 2007 ident: 10.1016/j.neunet.2020.11.005_b47 article-title: Spike-timing-dependent plasticity in balanced random networks publication-title: Neural Computation doi: 10.1162/neco.2007.19.6.1437 – volume: 38 start-page: 82 issue: 1 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b14 article-title: Loihi: A neuromorphic Manycore processor with On-Chip Learning publication-title: IEEE Micro doi: 10.1109/MM.2018.112130359 – volume: 12 start-page: 288 issue: 3 year: 2013 ident: 10.1016/j.neunet.2020.11.005_b60 article-title: Immunity to device variations in a spiking neural network with memristive nanodevices publication-title: IEEE Transactions on Nanotechnology doi: 10.1109/TNANO.2013.2250995 – volume: 12 start-page: 114 issue: 2 year: 2013 ident: 10.1016/j.neunet.2020.11.005_b56 article-title: A scalable neuristor built with Mott memristors publication-title: Nature Materials doi: 10.1038/nmat3510 – volume: 10 start-page: 56 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b3 article-title: Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM) synapses publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2016.00056 – volume: 67 start-page: 1276 issue: 6 year: 1988 ident: 10.1016/j.neunet.2020.11.005_b24 article-title: Inelastic tunneling across thin amorphous films publication-title: Soviet Physics - JETP – volume: 2 start-page: 371 issue: 5 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b44 article-title: One-board design and simulation of double-layer perceptron based on metal-oxide memristive nanostructures publication-title: IEEE Transactions on Emerging Topics in Computational Intelligence doi: 10.1109/TETCI.2018.2829922 – year: 2019 ident: 10.1016/j.neunet.2020.11.005_b71 article-title: Reinforcement learning with analogue memristor arrays publication-title: Nature Electronics – volume: 31 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b20 article-title: Self-adaptive STDP-based learning of a spiking neuron with nanocomposite memristive weights publication-title: Nanotechnology doi: 10.1088/1361-6528/ab4a6d – volume: 86 start-page: 364 issue: 2 year: 2001 ident: 10.1016/j.neunet.2020.11.005_b63 article-title: Equilibrium properties of temporally asymmetric Hebbian plasticity publication-title: Physical Review Letters doi: 10.1103/PhysRevLett.86.364 – volume: 9 start-page: 2331 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b43 article-title: Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits publication-title: Neural Computation – year: 2019 ident: 10.1016/j.neunet.2020.11.005_b2 article-title: Probabilistic neural network with memristive crossbar circuits – volume: 10 start-page: 482 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b12 article-title: Analog memristive synapse in spiking networks implementing unsupervised learning publication-title: Frontiers in Neuroscience doi: 10.3389/fnins.2016.00482 – volume: 6 start-page: 21331 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b58 article-title: Self-adaptive Spike-Time-Dependent Plasticity of Metal-oxide memristors publication-title: Scientific Reports doi: 10.1038/srep21331 – year: 2018 ident: 10.1016/j.neunet.2020.11.005_b61 – volume: 9 start-page: 40420 issue: 46 year: 2017 ident: 10.1016/j.neunet.2020.11.005_b34 article-title: Analog synaptic behavior of a Silicon Nitride Memristor publication-title: ACS Applied Materials & Interfaces doi: 10.1021/acsami.7b11191 – year: 1949 ident: 10.1016/j.neunet.2020.11.005_b27 – volume: 2 start-page: 290 issue: 7 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b7 article-title: A fully integrated reprogrammable memristor–CMOS system for efficient multiply–accumulate operations publication-title: Nature Electronics doi: 10.1038/s41928-019-0270-x – volume: 453 start-page: 80 year: 2008 ident: 10.1016/j.neunet.2020.11.005_b68 article-title: The missing memristor found publication-title: Nature doi: 10.1038/nature06932 – year: 2016 ident: 10.1016/j.neunet.2020.11.005_b32 – volume: 1 start-page: 52 issue: 1 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b35 article-title: Analogue signal and image processing with large memristor crossbars publication-title: Nature Electronics doi: 10.1038/s41928-017-0002-z – volume: 54 start-page: 992 issue: 4 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b9 article-title: A 4096-Neuron 1M-Synapse 3.8-pJ/SOP spiking neural network with On-Chip STDP Learning and Sparse Weights in 10-nm FinFET CMOS publication-title: IEEE Journal of Solid-State Circuits doi: 10.1109/JSSC.2018.2884901 – volume: 102 start-page: 652 issue: 5 year: 2014 ident: 10.1016/j.neunet.2020.11.005_b21 article-title: The SpiNNaker project publication-title: Proceedings of the IEEE doi: 10.1109/JPROC.2014.2304638 – volume: 121 start-page: 88 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b37 article-title: Spiking Neural Networks and online learning: An overview and perspectives publication-title: Neural Networks doi: 10.1016/j.neunet.2019.09.004 – volume: 18 start-page: 309 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b73 article-title: Memristive crossbar arrays for brain-inspired computing publication-title: Nature Materials doi: 10.1038/s41563-019-0291-x – volume: 51 start-page: 34003 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b13 article-title: Spike-driven threshold-based learning with memristive synapses and neuromorphic silicon neurons publication-title: Journal of Physics D (Applied Physics) doi: 10.1088/1361-6463/aad361 – year: 2002 ident: 10.1016/j.neunet.2020.11.005_b22 – volume: 98 start-page: 459 year: 2008 ident: 10.1016/j.neunet.2020.11.005_b48 article-title: Phenomenological models of synaptic plasticity based on spike timing publication-title: Biological Cybernetics doi: 10.1007/s00422-008-0233-1 – volume: 39 start-page: 1 issue: 1 year: 1977 ident: 10.1016/j.neunet.2020.11.005_b17 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: The Journal of the Royal Statistical Society, Series B doi: 10.1111/j.2517-6161.1977.tb01600.x – volume: 64 start-page: 1035 issue: 10 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b53 article-title: Formation of a memristive array of crossbar-structures based on (Co40Fe40B20)x(LiNbO3)100-x Nanocomposite publication-title: Journal of Communications Technology and Electronics doi: 10.1134/S1064226919100103 – volume: 9 start-page: 5311 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b57 article-title: Spike-timing-dependent plasticity learning of coincidence detection with passively integrated memristive circuits publication-title: Neural Computation – volume: 116 start-page: 4123 issue: 10 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b69 article-title: Solving matrix equations in one step with cross-point resistive arrays publication-title: Proceedings of the National Academy of Sciences of the United States of America doi: 10.1073/pnas.1815682116 – volume: 15 start-page: 1511 year: 2003 ident: 10.1016/j.neunet.2020.11.005_b30 article-title: Relating STDP to BCM publication-title: Neural Computation doi: 10.1162/089976603321891783 – volume: 45 start-page: 386 issue: 4 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b52 article-title: Adaptive properties of spiking neuromorphic networks with synapses based on memristive elements publication-title: Technical Physics Letters doi: 10.1134/S1063785019040278 – start-page: 1357 year: 2009 ident: 10.1016/j.neunet.2020.11.005_b49 article-title: STDP enables spiking neurons to detect hidden causes of their inputs – volume: 25 start-page: 1 year: 2013 ident: 10.1016/j.neunet.2020.11.005_b26 article-title: Emergence of optimal decoding of population codes through STDP publication-title: Neural Computation doi: 10.1162/NECO_a_00446 – year: 2020 ident: 10.1016/j.neunet.2020.11.005_b54 article-title: Spike-timing-dependent and spike-shape-independent plasticities with dopamine-like modulation in nanocomposite memristive synapses publication-title: Physica Status Solidi (A) Applications and Materials Science – volume: 59 start-page: 81 issue: March year: 2017 ident: 10.1016/j.neunet.2020.11.005_b1 article-title: Hardware design of LIF with Latency neuron model with memristive STDP synapses publication-title: IEEE Transactions on Very Large Scale Integration (VLSI) Systems – volume: 120 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b40 article-title: Mimicking of pulse shape-dependent learning rules with a quantum dot memristor publication-title: Journal of Applied Physics doi: 10.1063/1.4963830 – ident: 10.1016/j.neunet.2020.11.005_b46 doi: 10.1109/IJCNN.2017.7966072 – volume: 31 start-page: 25 year: 2008 ident: 10.1016/j.neunet.2020.11.005_b8 article-title: Spike timing–dependent Plasticity: A Hebbian learning rule publication-title: Annual Review of Neuroscience doi: 10.1146/annurev.neuro.31.060407.125639 – volume: 20 start-page: 8812 issue: 23 year: 2000 ident: 10.1016/j.neunet.2020.11.005_b62 article-title: Stable Hebbian learning from spike timing-dependent plasticity publication-title: The Journal of Neuroscience doi: 10.1523/JNEUROSCI.20-23-08812.2000 – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2020.11.005_b72 article-title: A CMOS spiking neuron for Dense memristor-synapse connectivity for brain-inspired computing – volume: 44 start-page: 416 issue: 5 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b50 article-title: A precise algorithm of memristor switching to a state with preset resistance publication-title: Technical Physics Letters doi: 10.1134/S106378501805022X – volume: 122 start-page: 273 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b67 article-title: Perceptrons from memristors publication-title: Neural Networks doi: 10.1016/j.neunet.2019.10.013 – volume: 14 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b41 article-title: Multifilamentary character of anticorrelated capacitive and resistive switching in memristive structures based on (CoFeB)x(LiNbO3)100-x nanocomposite publication-title: Physical Review A – volume: 9 start-page: 10800 year: 2019 ident: 10.1016/j.neunet.2020.11.005_b45 article-title: Parylene Based Memristive Devices with Multilevel resistive switching for Neuromorphic applications publication-title: Scientific Reports doi: 10.1038/s41598-019-47263-9 – year: 2020 ident: 10.1016/j.neunet.2020.11.005_b59 article-title: Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks publication-title: Neural Computing and Applications doi: 10.1007/s00521-020-04755-4 – volume: 7 start-page: 12611 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b65 article-title: Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses publication-title: Neural Computation – volume: 116 year: 2020 ident: 10.1016/j.neunet.2020.11.005_b10 article-title: A recipe for creating ideal hybrid memristive-CMOS neuromorphic processing systems publication-title: Applied Physics Letters doi: 10.1063/1.5142089 – start-page: 2314 year: 2016 ident: 10.1016/j.neunet.2020.11.005_b39 article-title: Demonstration of spike timing dependent plasticity in CBRAM devices with silicon neurons – volume: 40 start-page: 557 issue: 1 year: 2017 ident: 10.1016/j.neunet.2020.11.005_b28 article-title: Inhibitory plasticity: Balance, control, and codependence publication-title: Annual Review of Neuroscience doi: 10.1146/annurev-neuro-072116-031005 – volume: 12 start-page: 79 year: 2018 ident: 10.1016/j.neunet.2020.11.005_b16 article-title: Recurrent spiking neural network learning based on a competitive maximization of neuronal activity publication-title: Frontiers in Neuroinformatics doi: 10.3389/fninf.2018.00079
SSID	ssj0006843
Score	2.6096973
Snippet	This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	64
SubjectTerms	Algorithms Hardware analog neuron Memristive STDP Memristor Models, Neurological Neural Networks, Computer Neuronal Plasticity - physiology Neurons - physiology Pattern Recognition, Automated - methods Probabilistic generative model Spiking neural network Unsupervised learning
Title	Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network
URI	https://dx.doi.org/10.1016/j.neunet.2020.11.005 https://www.ncbi.nlm.nih.gov/pubmed/33291017 https://www.proquest.com/docview/2468670895
Volume	134
WOSCitedRecordID	wos000603296800006&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/eLvHCXMwtV3JbtswECUapyhy6b6kS8ACvRkKJFLicgzaFG0PRgD74JtAilTjNFEMbwj69R2KpOQgMNIeehEMkZRMv8fhcPzIQegT06yidVEn1GYiyaU1MOYymuSZlrRKNTHGJ5vgo5GYTuVZkBUt23QCvGnEzY2c_1eo4R6A7bbO_gPc3UPhBnwG0OEKsMP1r4AfWaf8d2I4WOoar8hqxYTjyZezxM1axp2m6gKBw04-BBy4jEGSWTN0maWv2uG_scPlfObi6UN39CUA2njh-LZXO7pV0qeqdweXtELaPmI6sr_OFXTJmbpeYDuG9r_P7SZGcrfqw7sXa68tCLsmQoyCZFHW7KYYb1cFlwnh4rbhDWFMbzr9YeZ3LLoPLlwcQx-hF7CgJ87MH6ftZu3VFp7zqxZQSol0Zqaf3zrVYSzaQ_uEFzwdoP2T76fTH93MzURO4_bKVgN496UH6FF8zC5PZtdKpfVYJk_R47DUwCeeIs_QA9s8R09iGg8crPoL9LNjDO4Zg4ExuGcMDozBW4zBkTF41mCFe8bgwBjsGYMDL16i8dfTyedvSci_kVTg1qwSqhixTFYpr4k0uTGFzrShGYz7GlwfXWQqM3mVFkLrTDFdqFQLwZjVKVeMvkKD5rqxbxBWuoK5pOLSapVTKqHcGqNSWdckL1J1iGj8JcsqHE3vMqRcllGDeFF6KEoHBaxaS4DiECVdq7k_muWe-jyCVAb30ruNJXDtnpYfI6YlWF_3l5pq7PV6WZKcCcZTIaHOaw92910iT97uLHmHDvrR8h4NVou1_YAeVpvVbLk4Qnt8Ko4CR_8AMKyudA
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=Necessary+conditions+for+STDP-based+pattern+recognition+learning+in+a+memristive+spiking+neural+network&rft.jtitle=Neural+networks&rft.au=Demin%2C+V+A&rft.au=Nekhaev%2C+D+V&rft.au=Surazhevsky%2C+I+A&rft.au=Nikiruy%2C+K+E&rft.date=2021-02-01&rft.eissn=1879-2782&rft.volume=134&rft.spage=64&rft_id=info:doi/10.1016%2Fj.neunet.2020.11.005&rft_id=info%3Apmid%2F33291017&rft.externalDocID=33291017
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