Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype

Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on biomedical circuits and systems Jg. 13; H. 3; S. 579 - 591
Hauptverfasser: Yan, Yexin, Kappel, David, Neumarker, Felix, Partzsch, Johannes, Vogginger, Bernhard, Hoppner, Sebastian, Furber, Steve, Maass, Wolfgang, Legenstein, Robert, Mayr, Christian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.06.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1932-4545, 1940-9990, 1940-9990
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions, such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the second generation SpiNNaker system is designed to overcome this problem. Low-power advanced RISC machine (ARM) processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations, the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local static random access memory (SRAM), leads to 62% energy reduction compared to the case without accelerators and the use of external dynamic random access memory (DRAM). The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this paper paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.
AbstractList Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions, such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the second generation SpiNNaker system is designed to overcome this problem. Low-power advanced RISC machine (ARM) processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations, the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local static random access memory (SRAM), leads to 62% energy reduction compared to the case without accelerators and the use of external dynamic random access memory (DRAM). The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this paper paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.
Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions, such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the second generation SpiNNaker system is designed to overcome this problem. Low-power advanced RISC machine (ARM) processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations, the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local static random access memory (SRAM), leads to 62% energy reduction compared to the case without accelerators and the use of external dynamic random access memory (DRAM). The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this paper paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions, such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the second generation SpiNNaker system is designed to overcome this problem. Low-power advanced RISC machine (ARM) processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations, the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local static random access memory (SRAM), leads to 62% energy reduction compared to the case without accelerators and the use of external dynamic random access memory (DRAM). The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this paper paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.
Author Maass, Wolfgang
Hoppner, Sebastian
Furber, Steve
Legenstein, Robert
Mayr, Christian
Kappel, David
Partzsch, Johannes
Vogginger, Bernhard
Yan, Yexin
Neumarker, Felix
Author_xml – sequence: 1
  givenname: Yexin
  orcidid: 0000-0002-4267-7015
  surname: Yan
  fullname: Yan, Yexin
  email: yexin.yan@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 2
  givenname: David
  surname: Kappel
  fullname: Kappel, David
  email: david.kappel@phys.uni-goettingen.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 3
  givenname: Felix
  surname: Neumarker
  fullname: Neumarker, Felix
  email: felix.neumaerker@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 4
  givenname: Johannes
  orcidid: 0000-0002-6286-5064
  surname: Partzsch
  fullname: Partzsch, Johannes
  email: johannes.partzsch@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 5
  givenname: Bernhard
  orcidid: 0000-0001-9042-5405
  surname: Vogginger
  fullname: Vogginger, Bernhard
  email: Bernhard.Vogginger@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 6
  givenname: Sebastian
  orcidid: 0000-0002-9938-2736
  surname: Hoppner
  fullname: Hoppner, Sebastian
  email: sebastian.hoeppner@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
– sequence: 7
  givenname: Steve
  orcidid: 0000-0002-6524-3367
  surname: Furber
  fullname: Furber, Steve
  email: steve.furber@manchester.ac.uk
  organization: School of Computer Science, University of Manchester, Manchester, U.K
– sequence: 8
  givenname: Wolfgang
  orcidid: 0000-0002-1178-087X
  surname: Maass
  fullname: Maass, Wolfgang
  email: maass@igi.tugraz.at
  organization: Institute for Theoretical Computer Science, Technische Universität Graz, Graz, Austria
– sequence: 9
  givenname: Robert
  orcidid: 0000-0002-8724-5507
  surname: Legenstein
  fullname: Legenstein, Robert
  email: robert.legenstein@igi.tugraz.at
  organization: Institute for Theoretical Computer Science, Technische Universität Graz, Graz, Austria
– sequence: 10
  givenname: Christian
  surname: Mayr
  fullname: Mayr, Christian
  email: christian.mayr@tu-dresden.de
  organization: Technische Universität Dresden, Dresden, Germany
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30932847$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1KJDEUhYMo48_MCyhIgRs31eanklSW2jg6ICq2sw63U7egtLrSJimk337SduvCxZBFAvm-y-WcQ7I7-AEJOWZ0whg1F89X08vZhFNmJtxQVVG2Qw6YqWhpjKG767fgZSUruU8OY3yhVCpu-A-yL2j-qSt9QG6u27ZzHQ6peMJ3CE15BRGbYpbC6NIYoC8ee4gpM2lV-KGAYrbs7u_hFUPBi8fgk0-rJf4key30EX9t7yPy9_f18_S2vHu4-TO9vCudMDKVzsxryTRrkCEwp4yrK1erxig1bykIymvNTCuVNFQaDRJRK9GAFgBKAoojcr6Zuwz-bcSY7KKLDvseBvRjtDzHofMxMqNn39AXP4Yhb5cpwWpVaakzdbqlxvkCG7sM3QLCyn5GlIF6A7jgYwzY2hwFpM4PKUDXW0btug370YZdt2G3bWSVf1M_p_9XOtlIHSJ-CbXSshJS_APJBpL3
CODEN ITBCCW
CitedBy_id crossref_primary_10_1049_cds2_12160
crossref_primary_10_3389_fnins_2021_611300
crossref_primary_10_3390_electronics9101599
crossref_primary_10_3389_fnins_2022_1018006
crossref_primary_10_1016_j_neuroscience_2021_10_001
crossref_primary_10_1016_j_sse_2024_109033
crossref_primary_10_3389_fnins_2025_1511972
crossref_primary_10_1038_s41586_024_08253_8
crossref_primary_10_1002_advs_202402375
crossref_primary_10_1109_JETCAS_2020_3040248
crossref_primary_10_1016_j_csbj_2024_10_040
crossref_primary_10_1109_TNNLS_2025_3547774
crossref_primary_10_1016_j_matt_2023_03_016
crossref_primary_10_1016_j_neunet_2020_09_024
crossref_primary_10_3389_fnins_2021_709053
crossref_primary_10_1038_s41467_023_37097_5
crossref_primary_10_1109_TBCAS_2021_3089132
Cites_doi 10.1214/aoms/1177706645
10.3389/fnins.2015.00002
10.1371/journal.pcbi.1003846
10.3389/fnins.2018.00213
10.1038/nrn3061
10.1142/S0129183191001037
10.1371/journal.pbio.1002572
10.3389/fnins.2015.00227
10.1109/TBCAS.2017.2759700
10.3389/fnins.2018.00291
10.1016/j.neuron.2007.04.030
10.1109/ISCAS.2017.8050528
10.1109/JPROC.2014.2304638
10.1016/j.mejo.2008.12.005
10.3389/fnins.2018.00105
10.3389/fnins.2018.00840
10.1109/TBCAS.2014.2379294
10.1007/s13295-016-0026-2
10.3389/fnins.2018.00816
10.1523/JNEUROSCI.0603-08.2008
10.1109/MM.2018.112130359
10.1109/JPROC.2014.2313565
10.1109/JSSC.2007.914337
10.1523/ENEURO.0301-17.2018
10.3389/fnins.2018.00941
10.1016/j.parco.2015.01.002
10.3389/fnins.2018.00891
10.1109/IJCNN.2017.7966125
10.1038/nrn2258
10.1109/TNNLS.2016.2572164
10.1109/EBCCSP.2015.7300664
10.1109/JPROC.2014.2314454
10.1523/JNEUROSCI.6130-10.2011
10.1017/CBO9781107447615
10.1145/3061639.3062188
10.1145/945511.945517
10.1016/j.neuron.2016.10.046
10.3389/fnins.2015.00010
10.1109/TCSII.2013.2278123
10.1109/IEDM.2015.7409623
10.1371/journal.pcbi.1004485
10.3389/fnins.2013.00118
10.18637/jss.v008.i14
10.3389/fnins.2015.00141
10.1109/ISCAS.2017.8050530
10.1038/nature04783
10.1109/JSSC.2013.2259038
10.1126/science.1254642
10.1109/TCSII.2018.2824827
10.3389/fnins.2018.00434
10.1109/NORCHIP.2016.7792875
10.1109/IJCNN.2013.6706988
10.1145/2897937.2897986
10.1109/JPROC.2014.2310593
10.1016/j.neuron.2005.01.003
10.1098/rspb.2011.2629
10.1109/TBCAS.2016.2579164
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QO
7SP
7TB
8FD
FR3
L7M
P64
7X8
DOI 10.1109/TBCAS.2019.2906401
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Biotechnology Research Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
Advanced Technologies Database with Aerospace
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Biotechnology Research Abstracts
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Biotechnology Research Abstracts
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: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1940-9990
EndPage 591
ExternalDocumentID 30932847
10_1109_TBCAS_2019_2906401
8675435
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: EU's Horizon 2020 research and innovation programme
  grantid: 720270; 785907
– fundername: Austrian Science Fund
  grantid: I 3251-N33
  funderid: 10.13039/501100002428
– fundername: European Union Seventh Framework Programme
  grantid: 604102
– fundername: H2020-FETPROACT project
  grantid: 732266
– fundername: Austrian Science Fund FWF
  grantid: I 3251
GroupedDBID ---
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
RIG
7QO
7SP
7TB
8FD
FR3
L7M
P64
7X8
ID FETCH-LOGICAL-c395t-c9b85171de1ea1c69c84c86d966bf0a3028719f56590597a5ee763da73aa65ae3
IEDL.DBID RIE
ISICitedReferencesCount 25
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000469839700009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1932-4545
1940-9990
IngestDate Sun Sep 28 14:08:43 EDT 2025
Mon Jun 30 08:39:50 EDT 2025
Mon Jul 21 06:02:39 EDT 2025
Sat Nov 29 05:32:51 EST 2025
Tue Nov 18 22:16:38 EST 2025
Wed Aug 27 02:46:42 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c395t-c9b85171de1ea1c69c84c86d966bf0a3028719f56590597a5ee763da73aa65ae3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-6286-5064
0000-0001-9042-5405
0000-0002-9938-2736
0000-0002-4267-7015
0000-0002-8724-5507
0000-0002-6524-3367
0000-0002-1178-087X
OpenAccessLink https://ieeexplore.ieee.org/document/8675435
PMID 30932847
PQID 2231864757
PQPubID 85510
PageCount 13
ParticipantIDs proquest_miscellaneous_2201717195
crossref_primary_10_1109_TBCAS_2019_2906401
proquest_journals_2231864757
crossref_citationtrail_10_1109_TBCAS_2019_2906401
ieee_primary_8675435
pubmed_primary_30932847
PublicationCentury 2000
PublicationDate 2019-06-01
PublicationDateYYYYMMDD 2019-06-01
PublicationDate_xml – month: 06
  year: 2019
  text: 2019-06-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on biomedical circuits and systems
PublicationTitleAbbrev TBCAS
PublicationTitleAlternate IEEE Trans Biomed Circuits Syst
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref12
ref59
ref58
ref14
ref53
ref52
ref55
ref11
ref54
ref10
ref17
ref16
ref19
ref18
frenkel (ref64) 2019; 13
ref51
ref50
höppner (ref38) 2018
ref46
ref45
ref48
höppner (ref33) 0
ref41
ref44
ref43
henker (ref56) 0
ref8
ref7
han (ref49) 0
ref9
ref4
ref3
ref6
hopkins (ref47) 2014
ref5
ref40
ref35
höppner (ref32) 0
ref34
ref37
ref36
ref31
ref30
ref2
ref1
ref39
bellec (ref15) 0
ref24
ref67
ref23
ref26
ref25
ref20
ref63
ref66
ref22
noack (ref42) 0
ref65
ref21
ref28
ref27
ref29
kappel (ref13) 0
ref60
ref62
ref61
References_xml – start-page: 219
  year: 0
  ident: ref42
  article-title: Biology-derived synaptic dynamics and optimized system architecture for neuromorphic hardware
  publication-title: Proc 14th Int Conf Mixed Des Integr Circuits Syst
– ident: ref44
  doi: 10.1214/aoms/1177706645
– ident: ref24
  doi: 10.3389/fnins.2015.00002
– ident: ref9
  doi: 10.1371/journal.pcbi.1003846
– ident: ref60
  doi: 10.3389/fnins.2018.00213
– ident: ref10
  doi: 10.1038/nrn3061
– ident: ref46
  doi: 10.1142/S0129183191001037
– ident: ref5
  doi: 10.1371/journal.pbio.1002572
– start-page: 1135
  year: 0
  ident: ref49
  article-title: Learning both weights and connections for efficient neural networks
  publication-title: Proc 28th Int Conf Neural Inf Process Syst
– ident: ref18
  doi: 10.3389/fnins.2015.00227
– ident: ref59
  doi: 10.1109/TBCAS.2017.2759700
– ident: ref52
  doi: 10.3389/fnins.2018.00291
– ident: ref6
  doi: 10.1016/j.neuron.2007.04.030
– year: 2018
  ident: ref38
  article-title: Method for generating true random numbers on a multiprocessor system and the same
– ident: ref26
  doi: 10.1109/ISCAS.2017.8050528
– ident: ref27
  doi: 10.1109/JPROC.2014.2304638
– ident: ref37
  doi: 10.1016/j.mejo.2008.12.005
– ident: ref48
  doi: 10.3389/fnins.2018.00105
– ident: ref41
  doi: 10.3389/fnins.2018.00840
– start-page: 1
  year: 0
  ident: ref32
  article-title: SpiNNaker 2-Towards extremely efficient digital neuromorphics and multi-scale brain emulation
  publication-title: Proc 5th Neuro-Inspired Comput Elements Workshop
– ident: ref65
  doi: 10.1109/TBCAS.2014.2379294
– ident: ref4
  doi: 10.1007/s13295-016-0026-2
– ident: ref50
  doi: 10.3389/fnins.2018.00816
– ident: ref7
  doi: 10.1523/JNEUROSCI.0603-08.2008
– ident: ref61
  doi: 10.1109/MM.2018.112130359
– ident: ref58
  doi: 10.1109/JPROC.2014.2313565
– ident: ref55
  doi: 10.1109/JSSC.2007.914337
– ident: ref14
  doi: 10.1523/ENEURO.0301-17.2018
– ident: ref23
  doi: 10.3389/fnins.2018.00941
– ident: ref34
  doi: 10.1016/j.parco.2015.01.002
– ident: ref66
  doi: 10.3389/fnins.2018.00891
– ident: ref20
  doi: 10.1109/IJCNN.2017.7966125
– ident: ref1
  doi: 10.1038/nrn2258
– start-page: 1
  year: 0
  ident: ref15
  article-title: Deep rewiring: Training very sparse deep networks
  publication-title: Proc Int Conf Learn Representations
– ident: ref54
  doi: 10.1109/TNNLS.2016.2572164
– ident: ref43
  doi: 10.1109/EBCCSP.2015.7300664
– ident: ref67
  doi: 10.1109/JPROC.2014.2314454
– start-page: 1
  year: 0
  ident: ref33
  article-title: Dynamic voltage and frequency scaling for neuromorphic many-core systems
  publication-title: Proc IEEE Int Symp Circuits Syst
– ident: ref8
  doi: 10.1523/JNEUROSCI.6130-10.2011
– ident: ref40
  doi: 10.1017/CBO9781107447615
– ident: ref29
  doi: 10.1145/3061639.3062188
– ident: ref45
  doi: 10.1145/945511.945517
– year: 2014
  ident: ref47
– ident: ref30
  doi: 10.1016/j.neuron.2016.10.046
– ident: ref17
  doi: 10.3389/fnins.2015.00010
– ident: ref36
  doi: 10.1109/TCSII.2013.2278123
– volume: 13
  start-page: 145
  year: 2019
  ident: ref64
  article-title: A 0.086-mm$^2$ 12.7-pj/sop 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28-nm CMOS
  publication-title: IEEE Trans Biomed Circuits Syst
– ident: ref16
  doi: 10.1109/IEDM.2015.7409623
– start-page: 16
  year: 0
  ident: ref56
  article-title: Active pixel sensor arrays in 90/65nm CMOS-technologies with vertically stacked photodiodes
  publication-title: Proc IEEE Int Image Sensor Workshop
– ident: ref12
  doi: 10.1371/journal.pcbi.1004485
– ident: ref53
  doi: 10.3389/fnins.2013.00118
– ident: ref35
  doi: 10.18637/jss.v008.i14
– ident: ref63
  doi: 10.3389/fnins.2015.00141
– ident: ref21
  doi: 10.1109/ISCAS.2017.8050530
– ident: ref39
  doi: 10.1038/nature04783
– ident: ref31
  doi: 10.1109/JSSC.2013.2259038
– ident: ref22
  doi: 10.1126/science.1254642
– ident: ref19
  doi: 10.1109/TCSII.2018.2824827
– ident: ref57
  doi: 10.3389/fnins.2018.00434
– ident: ref25
  doi: 10.1109/NORCHIP.2016.7792875
– ident: ref51
  doi: 10.1109/IJCNN.2013.6706988
– ident: ref28
  doi: 10.1145/2897937.2897986
– start-page: 370
  year: 0
  ident: ref13
  article-title: Synaptic sampling: A Bayesian approach to neural network plasticity and rewiring
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref11
  doi: 10.1109/JPROC.2014.2310593
– ident: ref3
  doi: 10.1016/j.neuron.2005.01.003
– ident: ref2
  doi: 10.1098/rspb.2011.2629
– ident: ref62
  doi: 10.1109/TBCAS.2016.2579164
SSID ssj0056292
Score 2.3843753
Snippet Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 579
SubjectTerms Accelerators
Algorithms
Bayesian reinforcement learning
Biomedical materials
Brain
Brain - physiology
Brain modeling
Clocks
Computational modeling
Computer programs
Computer simulation
Dynamic random access memory
exponential function accelerator
Exponential functions
Generators
Hardware
Humans
Learning
Machine Learning
Mathematical models
Models, Neurological
Nervous system
Neural Networks, Computer
neuromorphic computing
Plastic properties
Plasticity
Prototypes
Random access memory
random number generator
Random numbers
Reinforcement
Silicon substrates
Software
SpiNNaker chip
Static random access memory
structural plasticity
Synapses - physiology
Synaptic plasticity
synaptic sampling
Task complexity
Title Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype
URI https://ieeexplore.ieee.org/document/8675435
https://www.ncbi.nlm.nih.gov/pubmed/30932847
https://www.proquest.com/docview/2231864757
https://www.proquest.com/docview/2201717195
Volume 13
WOSCitedRecordID wos000469839700009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1940-9990
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056292
  issn: 1932-4545
  databaseCode: RIE
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-QwDLYAcYADu8tzWBYFiRsU2knbNEdAsJxGIwakuVVp4koI1I6GAYl_j50-tAcWiVulOmkaJ_HnxPkMcCzjUhbD0AZYOhPEblgGhct0EJtC21LZxKHzySbUaJRNp3q8BKf9XRhE9MFneMaP_izf1faVt8rOM0K3ZN6XYVmptLmr1a26ZMZ9AmTGI8zjnXQXZEJ9fn95dTHhKC59xuTmcZsApjNCPqvK_wGmNzQ3P77XxJ-w0QJKcdGMgF-whNUmrP9DM7gFf689TwQVFHfoo2QvyXY5MfHcscy7IcYEojm-evEu6koYMZk9jkbmCediKMbzelHzVu02PNxc31_dBm0ChcBKnSwCqwsCVCpyGKGJbKptFtssdeTiFGVoZMjuki4J02lCWcokiLTcOKOkMWliUO7ASlVXuAfCapIjGSldGDuJGdWo0ojghHJp4coBRF2P5rZlF-ckF8-59zJCnXst5KyFvNXCAE76MrOGW-NL6S3u7l6y7ekBHHSKy9vp95IT5omyNFaJGsBR_5omDp-GmArrV5ZhqiD6f6pit1F4XzcfD7Pd3v_8m79hjVvWRIwdwAppC__Aqn1bPL7MD2l0TrNDPzo_ANU-30g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VFgk40EJ5LLTFSL1B2mTtxPGxrfpAlGjVXaTeIseeSBUoqbZbJP49M85DHACJW6SMHcdje76xx98A7EtVy2oauwhrbyPlp3VU-dxEylbG1dqlHn1INqGLIr--NrM1-DjehUHEEHyGB_wYzvJ96-55q-wwJ3RL5v0BbKRKTePuttaw7pIhDymQGZEwk3c6XJGJzeHi-ORoznFc5oDpzVWfAmYwQyGvyt8hZjA1Z5v_18gteNpDSnHUjYFnsIbNc3jyG9HgNpyfBqYIKiiuMMTJHpP18mIe2GOZeUPMCEZzhPXqp2gbYcX89qYo7DdciqmYLdtVy5u1L-Dr2eni5CLqUyhETpp0FTlTEaTSiccEbeIy43Ll8syTk1PVsZUxO0ymJlRnCGdpmyLSguOtltZmqUX5EtabtsHXIJwhOZKR0sfKS8ypRp0lBCi0zypfTyAZerR0Pb84p7n4XgY_IzZl0ELJWih7LUzgw1jmtmPX-Kf0Nnf3KNn39AR2BsWV_QS8Kwn1JHmmdKon8H58TVOHz0Nsg-09yzBZEP0_VfGqU_hYNx8Qs-V-8-dvvoNHF4svl-Xlp-LzW3jMrezix3ZgnTSHu_DQ_Vjd3C33whj9BVgQ4ac
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=Efficient+Reward-Based+Structural+Plasticity+on+a+SpiNNaker+2+Prototype&rft.jtitle=IEEE+transactions+on+biomedical+circuits+and+systems&rft.au=Yan%2C+Yexin&rft.au=Kappel%2C+David&rft.au=Neumarker%2C+Felix&rft.au=Partzsch%2C+Johannes&rft.date=2019-06-01&rft.pub=IEEE&rft.issn=1932-4545&rft.volume=13&rft.issue=3&rft.spage=579&rft.epage=591&rft_id=info:doi/10.1109%2FTBCAS.2019.2906401&rft.externalDocID=8675435
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4545&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4545&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4545&client=summon