Name
Abstract | ||
|---|---|---|
The conventional back-propagation (BP) algorithm is not suitable for building fault tolerant neural 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 based on 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 modified algorithm leads to significant enhancement in the network's ability to cope with internal hardware failures. |
Year | DOI | Venue |
|---|---|---|
1996 | null | IEEE International Conference on Neural Networks - Conference Proceedings |
Keywords | Field | DocType |
null | Computer science,Parallel processing,Algorithm,Automation,Redundancy (engineering),Fault tolerance,Artificial neural network,Backpropagation,Constrained optimization | Conference |
Volume | Issue | ISSN |
1 | null | null |
ISBN | Citations | PageRank |
0-7803-3210-5 | 2 | 0.36 |
References | Authors | |
4 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Naihong Wei | 1 | 2 | 0.69 |
| Shiyuan Yang | 2 | 51 | 15.08 |
| Shibai Tong | 3 | 2 | 1.71 |