Title :
Recovering faulty self-organizing neural networks: by weight shifting technique
Author :
Khunasaraphan, C. ; Tanprasert, T. ; Lursinsap, C.
Author_Institution :
Center for Adv. Comput. Studies, Southwestern Louisiana Univ., Lafayette, LA, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
A fault tolerant technique of feedforward neural networks, called weight shifting, and its analytical models are proposed. The technique is applied to recover a self-organized 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
Keywords :
fault tolerant computing; feedforward neural nets; self-organising feature maps; fault tolerant technique; faulty links; feedforward neural networks; recovery procedures; self-organizing neural networks; weight shifting; Computer errors; Computer networks; Fault detection; Fault tolerance; Feedforward systems; Mathematics; Neural networks; Neurons; Space technology; Very large scale integration;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374512
