Continuous attractors in recurrent neural networks and phase space learning
Tipo
Artigo de evento
Data de publicação
2000
Periódico
Proceedings - Brazilian Symposium on Neural Networks, SBRN
Citações (Scopus)
0
Autores
De Oliveira R.
Monteiro L.H.A.
Monteiro L.H.A.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
© 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.
Descrição
Palavras-chave
Assuntos Scopus
Associative memory , Chaotic attractors , Continuous attractor , Convergence , Genetic mutations , Limit-cycle , Recurrent networks , Training algorithms