Repositório Digital

A- A A+

Categorization in fully connected multistate neural network models

.

Categorization in fully connected multistate neural network models

Mostrar registro completo

Estatísticas

Título Categorization in fully connected multistate neural network models
Autor Erichsen Junior, Rubem
Theumann, Walter Karl
Dominguez, David Renato Carreta
Abstract The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multistate patterns in a two level structure of ancestors and descendents ~examples! are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q=3-state model and a Q=∞ state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The categorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained. [S1063-651X(99)09212-0]
Contido em Physical Review. E, Statistical Physics, Plasmas, Fluids and Related Interdisciplinary Topics. New York. Vol. 60, no. 6, pt. B (Dec. 1999), p. 7321-7331
Assunto Redes neurais de hopfield
Ruídos
Origem Estrangeiro
Tipo Artigo de periódico
URI http://hdl.handle.net/10183/101307
Arquivos Descrição Formato
000055631.pdf (123.4Kb) Texto completo (inglês) Adobe PDF Visualizar/abrir

Este item está licenciado na Creative Commons License

Este item aparece na(s) seguinte(s) coleção(ões)


Mostrar registro completo

Percorrer



  • O autor é titular dos direitos autorais dos documentos disponíveis neste repositório e é vedada, nos termos da lei, a comercialização de qualquer espécie sem sua autorização prévia.
    Projeto gráfico elaborado pelo Caixola - Clube de Criação Fabico/UFRGS Powered by DSpace software, Version 1.8.1.