Fuzzy Neural Network Models for Supervised Classification: Multispectral Image Analysis

摘要: Abstract It has been well established that neural networks provide a reasonable and powerful alternative to conventional classifiers. During the past few years there large energetic upswing in research efforts aimed at synthesizing fuzzy logic with networks. This combination of seems natural because two approaches generally attack design “intelligent” systems from quite different angles. Neural algorithms for learning, classification, optimization whereas deals issues such as reasoning on higher (semantic or linguistic) level. Consequently technologies complement each other. In this paper we propose novel fuzzy‐neural network models supervised learning. The first model consists three layers, second four layers. both models, layers implement membership functions remaining inference engine. Both use gr...