Information processing in synchronous neural networks / Processamento de informações em redes de neurônios sincronas

AUTOR(ES)

Jose Fernando Fontanari

DATA DE PUBLICAÇÃO

1988

RESUMO

Spin glasses are very complex systems characterized by a huge number of stable and metastable states. If we identify each state with a memorized information then spin glasses may be used as associative or content addressable memories. This spin glass model is then called a neural network. In this work we study the thermodynamics and some dynamical aspects of a neural network with parallel or synchronous processing - Littles model of associative memory -in the regime where the number of memorized informations p grows as p = αN, where N is the number of neurons. Using the replica symmetric theory we determine the phase diagram in the space of the models parameters, in which we include a neural self interaction term. The richness of the phase diagram which possesses a surface of tricritical points is due to the competition between the two asymptotic dynamical behaviours of the synchronous dynamics: fixed points and cycles of lenght two.

ASSUNTO(S)

mecânica estatística neural networks spin glasses memória associativa associative memory statistical mechanics redes neurais vidros de spin

Documentos Relacionados

• Self-organized phase transitions in neural networks as a neural mechanism of information processing.
• Processamento de informação em neurônios motores de um centro gerador de padrões
• Symbolic processing in neural networks
• Aspectos de mapas caóticos acoplados para processamento de informações
• Aspectos de mapas caóticos acoplados para processamento de informações