Extraction method of rules from reflective neural network architecture

Author

Ichimura, Takumi ; Matsumoto, Noboru ; Tazaki, Eiichiro ; Yoshida, Kenta

Author_Institution

Dept. of Control & Syst. Eng., Toin Univ. of Yokohama, Japan

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

510

Abstract

Reflective neural network is a new architecture with a learning procedure for systems composed of many networks based on a network module concept. To learn a subset of the complete set of training data, each module has two kinds of feedforward networks; a monitor network and a worker network. A monitor network estimates how good a worker network is for distributed training data. We propose an extraction method of fuzzy rules from the modified network based on the reflective neural network. To verify the validity and the effectiveness of the proposed method, we develop a medical diagnostic system for thyroid diseases

Keywords

feedforward neural nets; knowledge acquisition; learning (artificial intelligence); medical diagnostic computing; pattern classification; distributed training data; feedforward networks; learning procedure; medical diagnostic system; monitor network; network module concept; reflective neural network; rules extraction method; thyroid diseases; worker network; Adaptive systems; Control systems; Data mining; Diseases; Fuzzy neural networks; Medical control systems; Medical diagnosis; Monitoring; Neural networks; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611721

Filename

611721