Dynamic constructive fault tolerant algorithm for feedforward neural networks

This source preferred by Hammadi Nait-Charif

Authors: Nait-Charif, H., Ohmameuda, T., Kaneko, K. and Ito, H.

Journal: IEICE Transactions on Information and Systems

Volume: E81-D

Pages: 115-123

ISSN: 0916-8532

In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.

The data on this page was last updated at 05:30 on November 25, 2020.