WEIGHT SHIFTING TECHNIQUES FOR SELF-RECOVERY NEURAL NETWORKS

被引：16

作者：

KHUNASARAPHAN, C ^{[1
]}

VANAPIPAT, K ^{[1
]}

LURSINSAP, C ^{[1
]}

机构：

[1] UNIV SW LOUISIANA,CTR ADV COMP STUDIES,LAFAYETTE,LA 70504

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1994年 / 5卷 / 04期

基金：

美国国家科学基金会;

关键词：

Self recovery neural networks - Weight shifting techniques;

D O I：

10.1109/72.298234

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a self-recovery technique of feed-forward 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.

引用

页码：651 / 658

页数：8