Redes neurais recorrentes hipercomplexas e suas aplicações em reconstrução de imagens e classificação de padrões

Autor: Lobo Carrasco, Rodolfo Anibal, 1989

Publikováno v: Biblioteca Digital de Teses e Dissertações da Universidade Estadual de Campinas (UNICAMP)
Universidade Estadual de Campinas (UNICAMP)
instacron:UNICAMP

Orientador: Marcos Eduardo Ribeiro do Valle Mesquita Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica Resumo: As redes neurais hipercomplexas, incluindo redes neurais complexas, q

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::94741db8ee3c66cd5ef7ea640eacfd43

Categorization in a Hopfield network trained with weighted examples : extensive number of concepts

Autor: Costa, Rogerio Adeodato Lima, Theumann, Alba Graciela Rivas de

Publikováno v: Repositório Institucional da UFRGS
Universidade Federal do Rio Grande do Sul (UFRGS)
instacron:UFRGS

We consider the categorization problem in a Hopfield network with an extensive number of concepts p =αN and trained with s examples of weight λτ, T=1, . . . ,s in the presence of synaptic noise represented by a dimensionless ‘‘temperature’�

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::78b0930b26897f1bad9d7d896c651d1a

Categorization in fully connected multistate neural network models

Autor: Erichsen Junior, Rubem, Theumann, Walter Karl, Dominguez, David Renato Carreta

Publikováno v: Repositório Institucional da UFRGS
Universidade Federal do Rio Grande do Sul (UFRGS)
instacron:UFRGS

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 struct

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::568156555aacc1b8b458ab784b445f9b