Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Modeling reservoir computing with the discrete nonlinear Schrodinger equation
KTH, Skolan för teknikvetenskap (SCI), Tillämpad fysik, Material- och nanofysik.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Programvaruteknik och datorsystem, SCS. RISE SICS, Electrum 229, SE-16429 Kista, Sweden..ORCID-id: 0000-0001-7949-1815
KTH, Skolan för industriell teknik och management (ITM), Materialvetenskap, Tillämpad materialfysik. KTH, Centra, SeRC - Swedish e-Science Research Centre.ORCID-id: 0000-0001-7788-6127
2018 (engelsk)Inngår i: Physical review. E, ISSN 2470-0045, E-ISSN 2470-0053, Vol. 98, nr 5, artikkel-id 052101Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

We formulate, using the discrete nonlinear Schrodinger equation (DNLS), a general approach to encode and process information based on reservoir computing. Reservoir computing is a promising avenue for realizing neuromorphic computing devices. In such computing systems, training is performed only at the output level by adjusting the output from the reservoir with respect to a target signal. In our formulation, the reservoir can be an arbitrary physical system, driven out of thermal equilibrium by an external driving. The DNLS is a general oscillator model with broad application in physics, and we argue that our approach is completely general and does not depend on the physical realization of the reservoir. The driving, which encodes the object to be recognized, acts as a thermodynamic force, one for each node in the reservoir. Currents associated with these thermodynamic forces in turn encode the output signal from the reservoir. As an example, we consider numerically the problem of supervised learning for pattern recognition, using as a reservoir a network of nonlinear oscillators.

sted, utgiver, år, opplag, sider
AMER PHYSICAL SOC , 2018. Vol. 98, nr 5, artikkel-id 052101
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-239083DOI: 10.1103/PhysRevE.98.052101ISI: 000448929900001Scopus ID: 2-s2.0-85056391374OAI: oai:DiVA.org:kth-239083DiVA, id: diva2:1264905
Forskningsfinansiär
Swedish Energy Agency, STEM P40147-1Swedish Research Council, VR 2016-05980Swedish Research Council, VR 2016-01961Swedish Research Council, VR 2015-04608
Merknad

QC 20181121

Tilgjengelig fra: 2018-11-21 Laget: 2018-11-21 Sist oppdatert: 2019-08-20bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Borlenghi, SimoneBoman, MagnusDelin, Anna

Søk i DiVA

Av forfatter/redaktør
Borlenghi, SimoneBoman, MagnusDelin, Anna
Av organisasjonen
I samme tidsskrift
Physical review. E

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 327 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf