The role of excitatory and inhibitory learning in EXIN networks

• Autor(a) principal: Barreto, Guilherme de Alencar
• Data de Publicação: 1998
• Outros Autores: Araújo, Aluízio Fausto Ribeiro
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da Universidade Federal do Ceará (UFC)
• Texto Completo: http://www.repositorio.ufc.br/handle/riufc/70706
• topic: EXIN networks; Anti-hebbian learning; Competitive learning; Uncertainty; Distributed coding

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.