Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)
- 1998.06a
- /
- Pages.399-403
- /
- 1998
A New Fuzzy Supervised Learning Algorithm
- Kim, Kwang-Baek (Major in Computer Engineering, Division of Computer Information Engineering, Silla University) ;
- Yuk, Chang-Keun (Department of Computer Science, Pusan National University) ;
- Cha, Eui-Young (Department of Computer Science, Pusan National University)
- Published : 1998.06.01
Abstract
In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.
Keywords