Repositório Digital

A- A A+

Optimally adapted multistate neural networks trained with noise

.

Optimally adapted multistate neural networks trained with noise

Mostrar registro completo

Estatísticas

Título Optimally adapted multistate neural networks trained with noise
Autor Erichsen Junior, Rubem
Theumann, Walter Karl
Abstract The principle of adaptation in a noisy retrieval environment is extended here to a diluted attractor neural network of Q-state neurons trained with noisy data. The network is adapted to an appropriate noisy training overlap and training activity, which are determined self-consistently by the optimized retrieval attractor overlap and activity. The optimized storage capacity and the corresponding retriever overlap are considerably enhanced by an adequate threshold in the states. Explicit results for improved optimal performance and new retriever phase diagrams are obtained for Q=3 and Q=4, with coexisting phases over a wide range of thresholds. Most of the interesting results are stable to replica-symmetry-breaking fluctuations.
Contido em Physical Review. E, Statistical physics, plasmas, fluids and related interdisciplinary topics. New York. Vol. 59, no. 1 (Jan. 1999), p. 947-955
Assunto Biofísica
Fisica estatistica
Redes neurais
Transformacoes de ordem-desordem
Origem Estrangeiro
Tipo Artigo de periódico
URI http://hdl.handle.net/10183/103647
Arquivos Descrição Formato
000235925.pdf (145.6Kb) 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.