Pattern reconstruction and sequence processing in feed-forward layered neural networks near saturation
Visualizar/abrir
Data
2005Tipo
Abstract
The dynamics and the stationary states for the competition between pattern reconstruction and asymmetric sequence processing are studied here in an exactly solvable feed-forward layered neural network model of binary units and patterns near saturation. Earlier work by Coolen and Sherrington on a parallel dynamics far from saturation is extended here to account for finite stochastic noise due to a Hebbian and a sequential learning rule. Phase diagrams are obtained with stationary states and quas ...
The dynamics and the stationary states for the competition between pattern reconstruction and asymmetric sequence processing are studied here in an exactly solvable feed-forward layered neural network model of binary units and patterns near saturation. Earlier work by Coolen and Sherrington on a parallel dynamics far from saturation is extended here to account for finite stochastic noise due to a Hebbian and a sequential learning rule. Phase diagrams are obtained with stationary states and quasiperiodic nonstationary solutions. The relevant dependence of these diagrams and of the quasiperiodic solutions on the stochastic noise and on initial inputs for the overlaps is explicitly discussed. ...
Contido em
Physical review. E, Statistical, nonlinear, and soft matter physics. Vol. 72, no. 2 (Aug. 2005), 021908, 9 p.
Origem
Estrangeiro
Coleções
-
Artigos de Periódicos (39558)Ciências Exatas e da Terra (6036)
Este item está licenciado na Creative Commons License