Continuous attractors in recurrent neural networks and phase space learning

dc.contributor.authorDe Oliveira R.
dc.contributor.authorMonteiro L.H.A.
dc.date.accessioned2024-03-13T01:47:20Z
dc.date.available2024-03-13T01:47:20Z
dc.date.issued2000
dc.description.abstract© 2000 IEEE.Recurrent networks can be used as associative memories where the stored memories represent fixed points to which the dynamics of the network converges. These networks, however, also can present continuous attractors, as limit cycles and chaotic attractors. The use of these attractors in recurrent networks for the construction of associative memories is argued. We provide a training algorithm for continuous attractors and present some numerical results of the learning method which involves genetic algorithms.
dc.description.firstpage291
dc.description.volume2000-January
dc.identifier.doi10.1109/SBRN.2000.889763
dc.identifier.issn1522-4899
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/38056
dc.relation.ispartofProceedings - Brazilian Symposium on Neural Networks, SBRN
dc.rightsAcesso Restrito
dc.subject.otherlanguageAssociative memory
dc.subject.otherlanguageChaos
dc.subject.otherlanguageConvergence
dc.subject.otherlanguageGenetic algorithms
dc.subject.otherlanguageGenetic mutations
dc.subject.otherlanguageInformation processing
dc.subject.otherlanguageIntelligent networks
dc.subject.otherlanguageLearning systems
dc.subject.otherlanguageLimit-cycles
dc.subject.otherlanguageRecurrent neural networks
dc.titleContinuous attractors in recurrent neural networks and phase space learning
dc.typeArtigo de evento
local.scopus.citations0
local.scopus.eid2-s2.0-84950291326
local.scopus.subjectAssociative memory
local.scopus.subjectChaotic attractors
local.scopus.subjectContinuous attractor
local.scopus.subjectConvergence
local.scopus.subjectGenetic mutations
local.scopus.subjectLimit-cycle
local.scopus.subjectRecurrent networks
local.scopus.subjectTraining algorithms
local.scopus.updated2024-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84950291326&origin=inward
Arquivos