Fault Tolerance in Feed-Foward Artificial Neural Networks

TitleFault Tolerance in Feed-Foward Artificial Neural Networks
Publication TypeTechnical Report
Year of Publication1990
AuthorsSéquin, C. H., & Clay R. D.
Other Numbers595

The errors resulting from defective units and faulty weights in layered feed-forward ANN's are analyzed, and techniques to make these networks more robust against such failures are discussed. First, using some simple examples of pattern classification tasks and of analog function approximation, it is demonstrated that standard architectures subjected to normal backpropagation training techniques do not lead to any noteworthy fault tolerance. Additional, redundant hardware coupled with suitable new training techniques are necessary to achieve that goal. A simple and general procedure is then introduced that develops fault tolerance in neural networks: The type of failures that one might expect to occur during operation are introduced at random during the training of the network, and the resulting output errors are used in a standard way for backpropagation and weight adjustment. The result of this training method is a modified internal representation that is not only more robust to the type of failures encountered in training, but which is also more tolerant of faults for which the network has not been explicitly trained.

Bibliographic Notes

ICSI Technical Report TR-90-031

Abbreviated Authors

C. H. Sequin and R. D. Clay

ICSI Publication Type

Technical Report