Title :
Weight shifting techniques for self-recovery neural networks
Author :
Khunasaraphan, C. ; Vanapipat, K. ; Lursinsap, C.
Author_Institution :
Center for Adv. Comput. Studies, Southwestern Louisiana Univ., Lafayette, LA, USA
fDate :
7/1/1994 12:00:00 AM
Abstract :
In this paper, a self-recovery technique of feedforward neural networks called weight shifting and its analytical models are proposed. The technique is applied to recover a network when some faulty links and/or neurons occur during the operation. If some input links of a specific neuron are detected faulty, their weights will be shifted to healthy links of the same neuron. On the other hand, if a faulty neuron is encountered, then we can treat it as a special case of faulty links by considering all the output links of that neuron to be faulty. The aim of this technique is to recover the network in a short time without any retraining and hardware repair. We also propose the hardware architecture for implementing this technique
Keywords :
built-in self test; feedforward neural nets; neural chips; faulty links; feedforward neural networks; self-recovery neural networks; weight shifting techniques; Analytical models; Computer networks; Fault detection; Fault tolerance; Feedforward neural networks; Helium; Neural network hardware; Neural networks; Neurons; Very large scale integration;
Journal_Title :
Neural Networks, IEEE Transactions on
