Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant

Authors:
Tadayoshi Horita;Itsuo Takanami;Masatoshi Mori
Affiliations:
-;-;-
Venue:
IEICE - Transactions on Information and Systems
Year:
2008

Citing 5
Cited 1

Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator

ACM Transactions on Modeling and Computer Simulation (TOMACS) - Special issue on uniform random number generation
A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks

Neural Networks
On fault injection approaches for fault tolerance of feedforward neural networks

ATS '97 Proceedings of the 6th Asian Test Symposium
Fault Tolerant Constructive Algorithm For Feedforward Neural Networks

PRFTS '97 Proceedings of the 1997 Pacific Rim International Symposium on Fault-Tolerant Systems
Complete and partial fault tolerance of feedforward neural nets

IEEE Transactions on Neural Networks

Letters: An FPGA-based multiple-weight-and-neuron-fault tolerant digital multilayer perceptron

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in practical use. The abilities of fault-tolerance of the multilayer neural networks in practical use, are analyzed in the relationship between the output errors in learning phase and in practical use. The analytical result shows that the multilayer neural networks have complete (100%) fault-tolerance to multiple weight-and-neuron faults in practical use. The simulation results concerning the rate of successful learnings, the ability of fault-tolerance, and the learning time, are also shown.