Comparative fault tolerance of parallel distributed processing networks

Author

Segee, Bruce E. ; Carter, Michael J.

Author_Institution

Dept. of Electr. & Comput. Eng., Maine Univ., Orono, ME, USA

Volume

43

Issue

11

fYear

1994

fDate

11/1/1994 12:00:00 AM

Firstpage

1323

Lastpage

1329

Abstract

We propose a method for evaluating and comparing the fault tolerance of a wide variety of parallel distributed processing networks (more commonly referred to as artificial neural networks). Despite the fact that these computing networks are biologically inspired and share many features of biological neural networks, they are not inherently tolerant of the loss of processing elements. We examine two classes of networks, multilayer perceptrons and Gaussian radial basis function networks, and show that there is a marked difference in their operational fault tolerance. Furthermore, we show that fault tolerance is influenced by the training algorithm used and even the initial state of the network. Using an idea due to Sequin and Clay (1990), we show that training with intermittent, randomly selected faults can dramatically enhance the fault tolerance of radial basis function networks, while it yields only marginal improvement when used with multilayer perceptrons

Keywords

backpropagation; fault tolerant computing; feedforward neural nets; Gaussian radial basis function networks; artificial neural networks; backpropagation; biological neural networks; computing networks; fault tolerance; function approximation; multilayer perceptrons; neural networks; parallel distributed processing networks; robustness; training algorithm; Clocks; Communication switching; Computer networks; Delay effects; Distributed processing; Fault tolerance; Hardware; Parallel processing; Routing; Very large scale integration;

fLanguage

English

Journal_Title

Computers, IEEE Transactions on

Publisher

ieee

ISSN

0018-9340

Type

jour

DOI

10.1109/12.324565

Filename

324565