Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)
- 1993.06a
- /
- Pages.1017-1020
- /
- 1993
A New Effective Learning Algorithm for a Neo Fuzzy Neuron Model
- Yamakawa, Takeshi (Department of Control Engineering and Science Kyushu Institute of Technology) ;
- Kusanagi, Hiroaki (TAKANO, LTD.) ;
- Uchino, Eiji (Department of Control Engineering and Science Kyushu Institute of Technology) ;
- Miki, Tsutomu (Department of Control Engineering and Science Kyushu Institute of Technology)
- Published : 1993.06.01
Abstract
This paper describes a neo fuzzy neuron which was produced by a fusion of fuzzy logic and neuroscience. Some learning algorithms are presented. The guarantee for the global minimum on the error-weight space is proved by a reduction to absurdity. Enhanced is that the learning speed of the neo fuzzy neuron exceeds 100,000 times of that of conventional multi-layer neural networks.
Keywords