DocumentCode :
3451368
Title :
Evolutive fuzzy neural networks
Author :
Machado, Ricardo José ; Da Rocha, Armando Freitas
Author_Institution :
IBM Rio Sci. Center, Rio de Janeiro, Brazil
fYear :
1992
fDate :
8-12 Mar 1992
Firstpage :
493
Lastpage :
500
Abstract :
The authors describe the combination of fuzzy neural networks with genetic algorithms, producing a flexible and powerful learning paradigm, called evolutive learning. Evolutive learning combines as complementary tools both inductive learning through synaptic weight adjustment and deductive learning through the modification of the network topology to obtain the automatic adaptation of system knowledge to the problem domain environment. Algorithms for the development of an evolutive learning machine are presented. A fuzzy criterion based on entropy is proposed to select the architecture for a fuzzy neural network best suited to a specific problem domain
Keywords :
fuzzy logic; genetic algorithms; learning (artificial intelligence); neural nets; deductive learning; entropy; evolutive fuzzy neural networks; genetic algorithms; inductive learning; network topology modification; synaptic weight adjustment; system knowledge adaptation; Computer architecture; Engines; Entropy; Fuzzy logic; Fuzzy neural networks; Genetic algorithms; Humans; Machine learning; Network topology; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 1992., IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0236-2
Type :
conf
DOI :
10.1109/FUZZY.1992.258663
Filename :
258663
Link To Document :
بازگشت