Structural plasticity on an accelerated analog neuromorphic hardware system

In computational neuroscience, as well as in machine learning, neuromorphic devices promise an accelerated and scalable alternative to neural network simulations. Their neural connectivity and synaptic capacity depend on their specific design choices, but is always intrinsically limited. Here, we pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Billaudelle, Sebastian (VerfasserIn) , Cramer, Benjamin (VerfasserIn) , Petrovici, Mihai A. (VerfasserIn) , Schreiber, Korbinian (VerfasserIn) , Kappel, David (VerfasserIn) , Schemmel, Johannes (VerfasserIn) , Meier, Karlheinz (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 2021
In: Neural networks
Year: 2020, Jahrgang: 133, Pages: 11-20
ISSN:1879-2782
DOI:10.1016/j.neunet.2020.09.024
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.neunet.2020.09.024
Verlag, lizenzpflichtig, Volltext: http://www.sciencedirect.com/science/article/pii/S0893608020303555
Volltext
Verfasserangaben:Sebastian Billaudelle, Benjamin Cramer, Mihai A. Petrovici, Korbinian Schreiber, David Kappel, Johannes Schemmel, Karlheinz Meier

MARC

LEADER 00000caa a2200000 c 4500
001 1746319127
003 DE-627
005 20220819091800.0
007 cr uuu---uuuuu
008 210201r20212020xx |||||o 00| ||eng c
024 7 |a 10.1016/j.neunet.2020.09.024  |2 doi 
035 |a (DE-627)1746319127 
035 |a (DE-599)KXP1746319127 
035 |a (OCoLC)1341389945 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 29  |2 sdnb 
100 1 |a Billaudelle, Sebastian  |d 1991-  |e VerfasserIn  |0 (DE-588)118726153X  |0 (DE-627)1666378356  |4 aut 
245 1 0 |a Structural plasticity on an accelerated analog neuromorphic hardware system  |c Sebastian Billaudelle, Benjamin Cramer, Mihai A. Petrovici, Korbinian Schreiber, David Kappel, Johannes Schemmel, Karlheinz Meier 
264 1 |c 2021 
300 |a 10 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Available online: 12 October 2020 
500 |a Gesehen am 01.02.2021 
520 |a In computational neuroscience, as well as in machine learning, neuromorphic devices promise an accelerated and scalable alternative to neural network simulations. Their neural connectivity and synaptic capacity depend on their specific design choices, but is always intrinsically limited. Here, we present a strategy to achieve structural plasticity that optimizes resource allocation under these constraints by constantly rewiring the pre- and postsynaptic partners while keeping the neuronal fan-in constant and the connectome sparse. In particular, we implemented this algorithm on the analog neuromorphic system BrainScaleS-2. It was executed on a custom embedded digital processor located on chip, accompanying the mixed-signal substrate of spiking neurons and synapse circuits. We evaluated our implementation in a simple supervised learning scenario, showing its ability to optimize the network topology with respect to the nature of its training data, as well as its overall computational efficiency. 
534 |c 2020 
650 4 |a BrainScaleS 
650 4 |a Neural networks 
650 4 |a Receptive fields 
650 4 |a Spiking 
650 4 |a Structural plasticity 
700 1 |a Cramer, Benjamin  |d 1993-  |e VerfasserIn  |0 (DE-588)1125028068  |0 (DE-627)879345616  |0 (DE-576)483278572  |4 aut 
700 1 |a Petrovici, Mihai A.  |e VerfasserIn  |0 (DE-588)1072021005  |0 (DE-627)826788823  |0 (DE-576)433488700  |4 aut 
700 1 |a Schreiber, Korbinian  |d 1986-  |e VerfasserIn  |0 (DE-588)1187261408  |0 (DE-627)1666377716  |4 aut 
700 1 |a Kappel, David  |e VerfasserIn  |0 (DE-588)1103161482  |0 (DE-627)860785149  |0 (DE-576)470509783  |4 aut 
700 1 |a Schemmel, Johannes  |e VerfasserIn  |0 (DE-588)1025834607  |0 (DE-627)72488291X  |0 (DE-576)370821440  |4 aut 
700 1 |a Meier, Karlheinz  |d 1955-2018  |e VerfasserIn  |0 (DE-588)1025835115  |0 (DE-627)724884114  |0 (DE-576)370822269  |4 aut 
773 0 8 |i Enthalten in  |t Neural networks  |d Amsterdam : Elsevier, 1988  |g 133(2021), Seite 11-20  |h Online-Ressource  |w (DE-627)302468536  |w (DE-600)1491372-0  |w (DE-576)07971997X  |x 1879-2782  |7 nnas  |a Structural plasticity on an accelerated analog neuromorphic hardware system 
773 1 8 |g volume:133  |g year:2021  |g pages:11-20  |g extent:10  |a Structural plasticity on an accelerated analog neuromorphic hardware system 
856 4 0 |u https://doi.org/10.1016/j.neunet.2020.09.024  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u http://www.sciencedirect.com/science/article/pii/S0893608020303555  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20210201 
993 |a Article 
994 |a 2021 
998 |g 1025835115  |a Meier, Karlheinz  |m 1025835115:Meier, Karlheinz  |d 130000  |d 130700  |e 130000PM1025835115  |e 130700PM1025835115  |k 0/130000/  |k 1/130000/130700/  |p 7  |y j 
998 |g 1025834607  |a Schemmel, Johannes  |m 1025834607:Schemmel, Johannes  |d 130000  |d 130700  |e 130000PS1025834607  |e 130700PS1025834607  |k 0/130000/  |k 1/130000/130700/  |p 6 
998 |g 1187261408  |a Schreiber, Korbinian  |m 1187261408:Schreiber, Korbinian  |d 130000  |d 130700  |e 130000PS1187261408  |e 130700PS1187261408  |k 0/130000/  |k 1/130000/130700/  |p 4 
998 |g 1072021005  |a Petrovici, Mihai A.  |m 1072021005:Petrovici, Mihai A.  |d 130000  |d 130700  |e 130000PP1072021005  |e 130700PP1072021005  |k 0/130000/  |k 1/130000/130700/  |p 3 
998 |g 1125028068  |a Cramer, Benjamin  |m 1125028068:Cramer, Benjamin  |d 130000  |d 130700  |e 130000PC1125028068  |e 130700PC1125028068  |k 0/130000/  |k 1/130000/130700/  |p 2 
998 |g 118726153X  |a Billaudelle, Sebastian  |m 118726153X:Billaudelle, Sebastian  |d 130000  |d 130700  |e 130000PB118726153X  |e 130700PB118726153X  |k 0/130000/  |k 1/130000/130700/  |p 1  |x j 
999 |a KXP-PPN1746319127  |e 3846237248 
BIB |a Y 
SER |a journal 
JSO |a {"recId":"1746319127","name":{"displayForm":["Sebastian Billaudelle, Benjamin Cramer, Mihai A. Petrovici, Korbinian Schreiber, David Kappel, Johannes Schemmel, Karlheinz Meier"]},"note":["Available online: 12 October 2020","Gesehen am 01.02.2021"],"origin":[{"dateIssuedDisp":"2021","dateIssuedKey":"2021"}],"language":["eng"],"person":[{"role":"aut","display":"Billaudelle, Sebastian","given":"Sebastian","family":"Billaudelle"},{"role":"aut","display":"Cramer, Benjamin","given":"Benjamin","family":"Cramer"},{"given":"Mihai A.","family":"Petrovici","role":"aut","display":"Petrovici, Mihai A."},{"role":"aut","display":"Schreiber, Korbinian","given":"Korbinian","family":"Schreiber"},{"display":"Kappel, David","role":"aut","family":"Kappel","given":"David"},{"given":"Johannes","family":"Schemmel","role":"aut","display":"Schemmel, Johannes"},{"display":"Meier, Karlheinz","role":"aut","family":"Meier","given":"Karlheinz"}],"physDesc":[{"extent":"10 S."}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"id":{"doi":["10.1016/j.neunet.2020.09.024"],"eki":["1746319127"]},"title":[{"title_sort":"Structural plasticity on an accelerated analog neuromorphic hardware system","title":"Structural plasticity on an accelerated analog neuromorphic hardware system"}],"relHost":[{"note":["Gesehen am 22.05.23","Ungezählte Beil.: Supplement"],"disp":"Structural plasticity on an accelerated analog neuromorphic hardware systemNeural networks","language":["eng"],"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"Neural networks","subtitle":"the official journal of the International Neural Network Society, European Neural Network Society and Japanese Neural Network Society","title":"Neural networks"}],"recId":"302468536","origin":[{"dateIssuedKey":"1988","publisherPlace":"Amsterdam ; New York, NY [u.a.]","dateIssuedDisp":"1988-","publisher":"Elsevier ; Pergamon Press"}],"id":{"zdb":["1491372-0"],"issn":["1879-2782"],"eki":["302468536"]},"type":{"bibl":"periodical","media":"Online-Ressource"},"pubHistory":["1.1988- 24.2011; Vol. 25.2012 -"],"part":{"volume":"133","year":"2021","extent":"10","pages":"11-20","text":"133(2021), Seite 11-20"}}]} 
SRT |a BILLAUDELLSTRUCTURAL2021