Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/74967
Type: Artigo de periódico
Title: THE COMBINATORIAL NEURAL NETWORK - A CONNECTIONIST MODEL FOR KNOWLEDGE BASED SYSTEMS
Author: MACHADO, RJ
DAROCHA, AF
Abstract: This paper describes the Combinatorial Neural Model, a high order neural network suitable for classification tasks. The model is based on the fuzzy sets theory, neural sciences and expert knowledge analysis results. The model presents Interesting properties such as: modularity, explanation capacity, concomitant knowledge and data representation, high speed of training, incremental learning, generalization capacity, feature selection, processing of uncertain and Incomplete data, fault tolerance.
Subject: NEURAL NETWORKS
LEARNING
CONNECTIONIST EXPERT SYSTEMS
Country: EUA
Editor: Springer
Rights: fechado
Date Issue: 1991
Appears in Collections:Artigos e Materiais de Revistas Científicas - Unicamp

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.