Autors: MILOSAVLJEVIC,A., STOIMENOV,L., RANCIC.D. Title: An Algorithm for Automatic Generation of Fuzzy Neural Network based on Perception Frames Keywords: Fuzzy neural networks (FNN), Rule generation, Perception fra Abstract: In this paper we present an algorithm for automatic generation of fuzzy neural networks (FNN). Fuzzy neural networks are concept that integrates some features of the fuzzy logic and the artificial neural networks theory. Based on analysis of several different fuzzy neural networks models, uniform representation method is presented, and two basic types are identified: FNN based on perception frames, and FNN with independent rules. Presented algorithm supports rule generation of fuzzy neural network based on perception frames, while training for adaptation relies on gradient decent method,i.e. modified backpropagation algorithm. References Issue
|
Вид: публикация в национален форум