Trainable hardware for dynamical computing using error backpropagation through physical media.
Identifieur interne : 000107 ( Main/Curation ); précédent : 000106; suivant : 000108Trainable hardware for dynamical computing using error backpropagation through physical media.
Auteurs : Michiel Hermans [Belgique] ; Michaël Burm [Belgique] ; Thomas Van Vaerenbergh [Belgique] ; Joni Dambre [Belgique] ; Peter Bienstman [Belgique]Source :
- Nature communications ; 2015.
Abstract
Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation-a crucial step for tuning such systems towards a specific task-can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers.
DOI: 10.1038/ncomms7729
PubMed: 25801303
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000098
- to stream PubMed, to step Curation: Pour aller vers cette notice dans l'étape Curation :000098
- to stream PubMed, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :000049
- to stream Ncbi, to step Merge: Pour aller vers cette notice dans l'étape Curation :000D27
- to stream Ncbi, to step Curation: Pour aller vers cette notice dans l'étape Curation :000D27
- to stream Ncbi, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :000D27
- to stream Main, to step Merge: Pour aller vers cette notice dans l'étape Curation :000104
Links to Exploration step
pubmed:25801303Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Trainable hardware for dynamical computing using error backpropagation through physical media.</title>
<author><name sortKey="Hermans, Michiel" sort="Hermans, Michiel" uniqKey="Hermans M" first="Michiel" last="Hermans">Michiel Hermans</name>
<affiliation wicri:level="4"><nlm:affiliation>OPERA photonique, Université Libre de Bruxelles, Avenue F. Roosevelt 50, 1050 Brussels, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>OPERA photonique, Université Libre de Bruxelles, Avenue F. Roosevelt 50, 1050 Brussels</wicri:regionArea>
<placeName><region type="land" nuts="2">Vienne (Autriche)</region>
<settlement type="city">Vienne (Autriche)</settlement>
</placeName>
<orgName type="university">Université libre de Bruxelles</orgName>
</affiliation>
</author>
<author><name sortKey="Burm, Michael" sort="Burm, Michael" uniqKey="Burm M" first="Michaël" last="Burm">Michaël Burm</name>
<affiliation wicri:level="3"><nlm:affiliation>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Van Vaerenbergh, Thomas" sort="Van Vaerenbergh, Thomas" uniqKey="Van Vaerenbergh T" first="Thomas" last="Van Vaerenbergh">Thomas Van Vaerenbergh</name>
<affiliation wicri:level="3"><nlm:affiliation>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Dambre, Joni" sort="Dambre, Joni" uniqKey="Dambre J" first="Joni" last="Dambre">Joni Dambre</name>
<affiliation wicri:level="3"><nlm:affiliation>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Bienstman, Peter" sort="Bienstman, Peter" uniqKey="Bienstman P" first="Peter" last="Bienstman">Peter Bienstman</name>
<affiliation wicri:level="3"><nlm:affiliation>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2015">2015</date>
<idno type="doi">10.1038/ncomms7729</idno>
<idno type="RBID">pubmed:25801303</idno>
<idno type="pmid">25801303</idno>
<idno type="wicri:Area/PubMed/Corpus">000098</idno>
<idno type="wicri:Area/PubMed/Curation">000098</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000049</idno>
<idno type="wicri:Area/Ncbi/Merge">000D27</idno>
<idno type="wicri:Area/Ncbi/Curation">000D27</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000D27</idno>
<idno type="wicri:Area/Main/Merge">000104</idno>
<idno type="wicri:Area/Main/Curation">000107</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Trainable hardware for dynamical computing using error backpropagation through physical media.</title>
<author><name sortKey="Hermans, Michiel" sort="Hermans, Michiel" uniqKey="Hermans M" first="Michiel" last="Hermans">Michiel Hermans</name>
<affiliation wicri:level="4"><nlm:affiliation>OPERA photonique, Université Libre de Bruxelles, Avenue F. Roosevelt 50, 1050 Brussels, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>OPERA photonique, Université Libre de Bruxelles, Avenue F. Roosevelt 50, 1050 Brussels</wicri:regionArea>
<placeName><region type="land" nuts="2">Vienne (Autriche)</region>
<settlement type="city">Vienne (Autriche)</settlement>
</placeName>
<orgName type="university">Université libre de Bruxelles</orgName>
</affiliation>
</author>
<author><name sortKey="Burm, Michael" sort="Burm, Michael" uniqKey="Burm M" first="Michaël" last="Burm">Michaël Burm</name>
<affiliation wicri:level="3"><nlm:affiliation>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Van Vaerenbergh, Thomas" sort="Van Vaerenbergh, Thomas" uniqKey="Van Vaerenbergh T" first="Thomas" last="Van Vaerenbergh">Thomas Van Vaerenbergh</name>
<affiliation wicri:level="3"><nlm:affiliation>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Dambre, Joni" sort="Dambre, Joni" uniqKey="Dambre J" first="Joni" last="Dambre">Joni Dambre</name>
<affiliation wicri:level="3"><nlm:affiliation>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>ELIS Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Bienstman, Peter" sort="Bienstman, Peter" uniqKey="Bienstman P" first="Peter" last="Bienstman">Peter Bienstman</name>
<affiliation wicri:level="3"><nlm:affiliation>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium.</nlm:affiliation>
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>INTEC Department, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent</wicri:regionArea>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j">Nature communications</title>
<idno type="e-ISSN">2041-1723</idno>
<imprint><date when="2015" type="published">2015</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation-a crucial step for tuning such systems towards a specific task-can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/Main/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000107 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Curation/biblio.hfd -nk 000107 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Musique |area= OperaV1 |flux= Main |étape= Curation |type= RBID |clé= pubmed:25801303 |texte= Trainable hardware for dynamical computing using error backpropagation through physical media. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Curation/RBID.i -Sk "pubmed:25801303" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Curation/biblio.hfd \ | NlmPubMed2Wicri -a OperaV1
This area was generated with Dilib version V0.6.21. |