Manipulation of hidden units activities for fault tolerant multi-layer neural networks

Author

Katsuda, Yusei ; Takase, Haruhiko ; Kita, Hidehiko ; Hayashi, Terumine

Author_Institution

Dept. of Electr. & Electron. Eng., Mie Univ., Japan

Volume

1

fYear

2003

fDate

16-20 July 2003

Firstpage

19

Abstract

We propose a new training algorithm to enhance fault tolerance of multi-layer neural networks (MLNs). This method is based on the fact that faults on connections between hidden layer and output layer have a harmful effect on fault tolerance of MLNs. to decrease these effects, we introduced two approaches, (1) reduce the number of strong connections between hidden layer and output layer, (2) neutralize the activities of hidden units. The first approach aims to reduce the undesirable connections. The second one aims to increase redundancy of internal representation.

Keywords

fault tolerance; learning (artificial intelligence); multilayer perceptrons; fault tolerant; hidden unit activity manipulation; internal representation redundancy; multilayer neural networks; undesirable connection reduction; Artificial neural networks; Degradation; Fault tolerance; Multi-layer neural network; Neural networks; Output feedback; Redundancy;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on

Print_ISBN

0-7803-7866-0

Type

conf

DOI

10.1109/CIRA.2003.1222056

Filename

1222056