期刊名称：International Journal of Computer Technology and Applications
电子版ISSN：2229-6093
出版年度：2013
卷号：4
期号：5
页码：772-784
出版社：Technopark Publications
摘要：Simplified Fuzzy ARTMAP is an architecture which synthesizes Fuzzy Logic with ART Neural Networks. This is one of the most researched form of Neuro-Fuzzy hybrid system and has resulted in a stupendous quantity of publications and research results. The existing Simplified Fuzzy ARTMAP architecture is based on traditional Zadehian Theory of Fuzzy sets where it is believed that there is no difference between Fuzzy membership function and Fuzzy membership value for the complement of a Fuzzy set which is already proved to be wrong. In this article, our objective is to present a new architecture of Simplified Fuzzy ARTMAP with the help of extended definition of complementation of Fuzzy sets using reference function. Our proposed architecture is based on the fact that Fuzzy membership function and Fuzzy membership value for the complement of a Fuzzy set are two different things. Also, an effort has been put forward to demonstrate the application of the proposed architecture with the evaluation of some example data
关键词：Complement of a Fuzzy set; Fuzzy membership function; Fuzzy membership value; Fuzzy reference function; Fuzzy set; Simplified Fuzzy ARTMAP
