Show simple item record

dc.contributor.author
Giulioni, Massimiliano
dc.contributor.author
Corradi, Federico
dc.contributor.author
Dante, Vittorio
dc.contributor.author
Del Giudice, Paolo
dc.date.accessioned
2018-10-12T15:53:44Z
dc.date.available
2017-06-11T20:12:55Z
dc.date.available
2018-10-12T15:53:44Z
dc.date.issued
2015-10-14
dc.identifier.other
10.1038/srep14730
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/105627
dc.identifier.doi
10.3929/ethz-b-000105627
dc.description.abstract
Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Nature Publishing Group
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Learning algorithms
en_US
dc.subject
Electrical and electronic engineering
en_US
dc.subject
Dynamical systems
en_US
dc.title
Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
ethz.journal.title
Scientific Reports
ethz.journal.volume
5
en_US
ethz.pages.start
14730
en_US
ethz.size
10 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.identifier.nebis
006751867
ethz.publication.place
London
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
03453 - Douglas, Rodney J.
en_US
ethz.leitzahl.certified
03453 - Douglas, Rodney J.
ethz.date.deposited
2017-06-11T20:13:08Z
ethz.source
ECIT
ethz.identifier.importid
imp593653966b69639305
ethz.ecitpid
pub:165393
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2017-07-13T03:04:53Z
ethz.rosetta.lastUpdated
2019-01-02T14:31:53Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Real%20time%20unsupervised%20learning%20of%20visual%20stimuli%20in%20neuromorphic%20VLSI%20systems&rft.jtitle=Scientific%20Reports&rft.date=2015-10-14&rft.volume=5&rft.spage=14730&rft.au=Giulioni,%20Massimiliano&Corradi,%20Federico&Dante,%20Vittorio&Del%20Giudice,%20Paolo&rft.genre=article&
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record