Proceedings of the Korean Institute of Information and Commucation Sciences Conference (한국정보통신학회:학술대회논문집)
- 2004.05a
- /
- Pages.1-5
- /
- 2004
Enhanced Fuzzy Multi-Layer Perceptron
- Kim, Kwang-Baek (Dept. of Computer Science, Silla University) ;
- Park, Choong-Sik (Faculty of Computer Information Eng., Youngdong University) ;
- Abhjit Pandya (Department of Computer Science and Engineering, Florida Atlantic University)
- Published : 2004.05.01
Abstract
In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the. proposed method to the problem of recognizing ID number in student identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.
Keywords