BDBComp
Parceria:
SBC
Energy Analysis of Hierarchically Coupled Generalized-Brain-State-in-Box (GBSB) Neural Network

Rogério M. GomesAntônio P. BragaHenrique E. Borges

Recent studies in neuroscience have revealed, by means of experimental evidences, that memory processes can be described as being organized, functionally, in hierarchical levels, where higher levels would coordinate sets of functions of the lower levels. In this paper we propose a multi-level memory based on coupled generalized-brain-state-in-a-box (GBSB) neural networks. Furthermore, we perform an energy analysis of such coupled system showing that the coupling does not destroy the first-level memory structures. A simulation was carried out to illustrate the behaviour of the system energy, for a wide range of the system parameters. The results obtained shows that, even when the neural networks are weakly coupled, the system still evolves to a state of minimum energy.

http://www.lbd.dcc.ufmg.br/colecoes/enia/2005/014.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD