Unsupervised context-based learning of multiple temporal sequences

Detalhes bibliográficos
Autor(a) principal: Barreto, Guilherme de Alencar
Data de Publicação: 1999
Outros Autores: Araújo, Aluízio Fausto Ribeiro
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da Universidade Federal do Ceará (UFC)
Texto Completo: http://www.repositorio.ufc.br/handle/riufc/70684
Resumo: A self-organizing neural network is proposed to handle multiple temporal sequences with states in common. The proposed network combines context-based competitive learning with time-delayed Hebbian learning to encode spatial features and temporal order of sequence items. A responsibility function to avoid catastrophic forgetting, and a redundancy mechanism to provide noise and fault tolerance increase the reliability of the model. States shared by different sequences are encoded by a single neuron, whereas context information indicates the correct sequence to be recalled in the case of ambiguity. Simulations with trajectories of a PUMA 560 robot are performed to test the network accuracy, robustness to noise and tolerance to faults.
id UFC-7_6571648cb9c499877075199805397f3e
oai_identifier_str oai:repositorio.ufc.br:riufc/70684
network_acronym_str UFC-7
network_name_str Repositório Institucional da Universidade Federal do Ceará (UFC)
repository_id_str
spelling Unsupervised context-based learning of multiple temporal sequencesA self-organizing neural network is proposed to handle multiple temporal sequences with states in common. The proposed network combines context-based competitive learning with time-delayed Hebbian learning to encode spatial features and temporal order of sequence items. A responsibility function to avoid catastrophic forgetting, and a redundancy mechanism to provide noise and fault tolerance increase the reliability of the model. States shared by different sequences are encoded by a single neuron, whereas context information indicates the correct sequence to be recalled in the case of ambiguity. Simulations with trajectories of a PUMA 560 robot are performed to test the network accuracy, robustness to noise and tolerance to faults.International Joint Conference on Neural Networks2023-02-09T14:17:33Z2023-02-09T14:17:33Z1999info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectapplication/pdfBARRETO, G. A.; ARAÚJO, A. F. R. Unsupervised context-based learning of multiple temporal sequences. In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, 1999, Washington, D.C. Anais... Washington, D.C.: IEEE, 1999. p. 1102-1106.http://www.repositorio.ufc.br/handle/riufc/70684Barreto, Guilherme de AlencarAraújo, Aluízio Fausto Ribeiroengreponame:Repositório Institucional da Universidade Federal do Ceará (UFC)instname:Universidade Federal do Ceará (UFC)instacron:UFCinfo:eu-repo/semantics/openAccess2023-02-09T14:17:33Zoai:repositorio.ufc.br:riufc/70684Repositório InstitucionalPUBhttp://www.repositorio.ufc.br/ri-oai/requestbu@ufc.br || repositorio@ufc.bropendoar:2023-02-09T14:17:33Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)false
dc.title.none.fl_str_mv Unsupervised context-based learning of multiple temporal sequences
title Unsupervised context-based learning of multiple temporal sequences
spellingShingle Unsupervised context-based learning of multiple temporal sequences
Barreto, Guilherme de Alencar
title_short Unsupervised context-based learning of multiple temporal sequences
title_full Unsupervised context-based learning of multiple temporal sequences
title_fullStr Unsupervised context-based learning of multiple temporal sequences
title_full_unstemmed Unsupervised context-based learning of multiple temporal sequences
title_sort Unsupervised context-based learning of multiple temporal sequences
author Barreto, Guilherme de Alencar
author_facet Barreto, Guilherme de Alencar
Araújo, Aluízio Fausto Ribeiro
author_role author
author2 Araújo, Aluízio Fausto Ribeiro
author2_role author
dc.contributor.author.fl_str_mv Barreto, Guilherme de Alencar
Araújo, Aluízio Fausto Ribeiro
description A self-organizing neural network is proposed to handle multiple temporal sequences with states in common. The proposed network combines context-based competitive learning with time-delayed Hebbian learning to encode spatial features and temporal order of sequence items. A responsibility function to avoid catastrophic forgetting, and a redundancy mechanism to provide noise and fault tolerance increase the reliability of the model. States shared by different sequences are encoded by a single neuron, whereas context information indicates the correct sequence to be recalled in the case of ambiguity. Simulations with trajectories of a PUMA 560 robot are performed to test the network accuracy, robustness to noise and tolerance to faults.
publishDate 1999
dc.date.none.fl_str_mv 1999
2023-02-09T14:17:33Z
2023-02-09T14:17:33Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv BARRETO, G. A.; ARAÚJO, A. F. R. Unsupervised context-based learning of multiple temporal sequences. In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, 1999, Washington, D.C. Anais... Washington, D.C.: IEEE, 1999. p. 1102-1106.
http://www.repositorio.ufc.br/handle/riufc/70684
identifier_str_mv BARRETO, G. A.; ARAÚJO, A. F. R. Unsupervised context-based learning of multiple temporal sequences. In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, 1999, Washington, D.C. Anais... Washington, D.C.: IEEE, 1999. p. 1102-1106.
url http://www.repositorio.ufc.br/handle/riufc/70684
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv International Joint Conference on Neural Networks
publisher.none.fl_str_mv International Joint Conference on Neural Networks
dc.source.none.fl_str_mv reponame:Repositório Institucional da Universidade Federal do Ceará (UFC)
instname:Universidade Federal do Ceará (UFC)
instacron:UFC
instname_str Universidade Federal do Ceará (UFC)
instacron_str UFC
institution UFC
reponame_str Repositório Institucional da Universidade Federal do Ceará (UFC)
collection Repositório Institucional da Universidade Federal do Ceará (UFC)
repository.name.fl_str_mv Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)
repository.mail.fl_str_mv bu@ufc.br || repositorio@ufc.br
_version_ 1809935815822802944

Registros relacionados