Phase Oscillatory Network and Visual Pattern Recognition

Autor(es)

Follmann, Rosangela ^[1] ; Macau, Elbert E. N. ^[2] ; Rosa, Jr., Epaminondas ^[3] ; Piqueira, Jose R. C. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Polytech Sch, Dept Telecommun & Control Engn, BR-05508010 Sao Paulo - Brazil

^[2] Brazilian Natl Inst Space Res, BR-12227010 Sao Jose Dos Campos - Brazil

^[3] Illinois State Univ, Dept Phys, Normal, IL 61761 - USA

• Tipo de documento: Artigo Científico
• Fonte: IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS; v. 26, n. 7, p. 1539-1544, JUL 2015.
• Citações Web of Science: 10

Resumo

We explore a properly interconnected set of Kuramoto type oscillators that results in a new associative-memory network configuration, which includes second-and third-order additional terms in the Fourier expansion of the network's coupling. Investigation of the response of the network to different external stimuli indicates an increase in the network capability for coding and information retrieval. Comparison of the network output with that of an equivalent experiment with subjects, for recognizing perturbed binary patterns, shows comparable results between the two approaches. We also discuss the enhanced storage capacity of the network. (AU)

• Processo FAPESP: 11/50151-0 - Fenômenos dinâmicos em redes complexas: fundamentos e aplicações
• Beneficiário: Elbert Einstein Nehrer Macau
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 11/13871-4 - Estudo de Sincronização de fase em Redes de Osciladores e aplicações à recuperação de Informações
• Beneficiário: Rosângela Follmann Bageston
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado