Knowledge based approach to structure level adaptation of neural networks

Author

Ichimura, Takumi ; Ooba, Kazuhiro ; Tazaki, Eiichiro ; Takahashi, Hidetaka ; Yoshida, Katusmi

Author_Institution

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

Volume

1

fYear

1997

fDate

12-15 Oct 1997

Firstpage

548

Abstract

This paper presents knowledge based approach to structure level adaptation of neural network. This algorithm determines a network structure based on prior knowledge and generates and/or annihilates hidden neurons of the network to reach good structure during learning phase. Furthermore, we present a method of extraction of fuzzy rules from the regularities of the network, since the network structure is one of optimal network structures. To verify the effectiveness of the proposed method, we developed a model of the occurrence of hypertension and extracted fuzzy rules from the network

Keywords

fuzzy systems; knowledge acquisition; knowledge based systems; learning (artificial intelligence); medical diagnostic computing; neural nets; fuzzy rule extraction; hidden neurons; hypertension; knowledge based systems; learning; medical diagnostic system; network structures; neural network; structure level adaptation; Artificial neural networks; Control systems; Data mining; Hypertension; Intelligent networks; Medical control systems; Medical diagnostic imaging; Neural networks; Neurons; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on

Conference_Location

Orlando, FL

ISSN

1062-922X

Print_ISBN

0-7803-4053-1

Type

conf

DOI

10.1109/ICSMC.1997.625809

Filename

625809