Use este identificador para citar ou linkar para este item:
http://repositorio.ufc.br/handle/riufc/70706
Tipo: | Artigo de Evento |
Título: | The role of excitatory and inhibitory learning in EXIN networks |
Autor(es): | Barreto, Guilherme de Alencar Araújo, Aluízio Fausto Ribeiro |
Palavras-chave: | EXIN networks;Anti-hebbian learning;Competitive learning;Uncertainty;Distributed coding |
Data do documento: | 1998 |
Instituição/Editor/Publicador: | World Congress on Computational Intelligence |
Citação: | BARRETO, G. A.; ARAÚJO, A. F. R. The role of excitatory and inhibitory learning in EXIN networks. In: WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, Anchorage. Anais... Anchorage: IEEE, 1998. p. 2378-2383. |
Abstract: | In this paper we propose modifications for the learning rules of Marshall’s EXIN (excitatory + inhibitory) neural network model in order to decrease its computational complexity and understand the role of the weight updating learning rules in correctly encoding familiar, superimposed and ambiguous input patterns. The MEXIN (Modified EXIN) models introduce mixtures of competitive and Hebbian updating rules. In this case, only the weights of the unit with highest activation are updated. Hence, the MEXIN networks require less computation than the original EXIN model. A number of simulations are carried out with the aim of showing how the models respond to overlapping, superimposed and ambiguous patterns. |
URI: | http://www.repositorio.ufc.br/handle/riufc/70706 |
Aparece nas coleções: | DETE - Trabalhos apresentados em eventos |
Arquivos associados a este item:
Arquivo | Descrição | Tamanho | Formato | |
---|---|---|---|---|
1998_eve_gabarreto.pdf | 123,94 kB | Adobe PDF | Visualizar/Abrir |
Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.