The conventional back-propagation (BP) algorithm is not suitable for building fault tolerant networks, since it usually develops non-uniform weights. In this paper, a learning method to improve the fault tolerance in classification is therefore presented and a metric is devised to evaluate the performance. The new method is basedon the BP algorithm. During the training, the magnitude of each weight is restrained from over-increasing. This modification enforces that the information be distributed across weights more evenly. Simulation results demonstrate that the modifed algorithm leads to significant enhancement in the network's ability to cope with internal hardware failures.
展开▼