Sign in
Back
A method for training feed forward neural network to be fault tolerant
Conference proceeding

A method for training feed forward neural network to be fault tolerant

H. Elsimary, S. Mashali, S. Shaheen and IEEE
Proceedings of IEEE Virtual Reality Annual International Symposium, pp.436-441
1993
DOI: https://doi.org/10.1109/VRAIS.1993.380747

Abstract

Artificial neural networks Backpropagation algorithms Computer networks Fault tolerance Fault tolerant systems Feedforward neural networks Feeds Neural network hardware Neural networks Predictive models
A method for training a feedforward neural network to be fault tolerant against weight perturbations is described. The measure for fault tolerance is the deviation of the network's output after training, when each interconnection weight is perturbed, from that output without perturbation. In this method, an attempt is made to keep that deviation as low as possible. This measure is used because it can represent that kinds of error which arises when neural networks are implemented in hardware.< >

Metrics

3 Record Views

Details