Evaluation function for fault tolerant multi-layer neural networks
Authors:
- T. ShinogiTST. Shinogi
- T. HayashiTHT. Hayashi
- H. KitaHKH. Kita
- 1 January 2000
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10987576) , 521-526 vol.3
Abstract
We propose a new learning algorithm to enhance fault tolerance of multilayer neural networks (MLN). This method is based on the idea that strong weights make MLN sensitive to faults. The purpose of the proposed algorithm is to make weights as small as possible through its training. The evaluation function of the proposed algorithm consists of not only the output error but also the square sum of weights. With the new evaluation function the learning algorithm minimizes not only output error but also weights. We discussed about the value of parameter to balance effects of these two terms. Next, we apply it to pattern recognition problems. As a result, it is shown that the degradation of recognition ratio is improved.Keywords
This publication has 4 references indexed in Scilit:
- On fault injection approaches for fault tolerance of feedforward neural networks2002
- Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during trainingIEEE Transactions on Neural Networks, 1994
- Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition applicationIEEE Transactions on Neural Networks, 1993
- Fault models for artificial neural networks1991