Structural learning of recurrent RBF networks with M-apoptosis

Author

Honda, Katsuhiro ; Miyoshi, Tetsuya ; Ichihashi, Hidetomo

Author_Institution

Osaka Prefectural Univ., Sakai, Japan

Volume

3

fYear

1998

fDate

4-9 May 1998

Firstpage

2390

Abstract

The apoptosis is an active form of cell death which plays an important role during embryonic development. We propose a unified approach, called M-apoptosis, to the structural learning of recurrent RBF networks. Minkowski norm of the first order derivatives of RBF networks with respect to input variables is added to the cost function for determining the unknown parameters. The parameters are changed so that the MSE and the first order derivatives become small during the learning process. After learning, the input variables of the units with small first order derivatives are deleted

Keywords

feedforward neural nets; learning (artificial intelligence); recurrent neural nets; Minkowski norm; RBF neural networks; apoptosis; cost function; first order derivatives; recurrent neural networks; structural learning; Biological neural networks; Computer architecture; Cost function; Embryo; Equations; Input variables; Neural networks; Radial basis function networks; Recurrent neural networks; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.687236

Filename

687236