Prediction Error of a Fault Tolerant Neural Network
For more than a decade, prediction error has been one powerful tool to measure the performance of a neural network. In this paper, we extend the technique to a kind of fault tolerant neural network. Consider a neural network to be suffering from multiple-node fault, a formulae similar to that of Generalized Prediction Error has been derived. Hence, the effective number of parameter of such a fault tolerant neural network is obtained. A difficulty in obtaining the mean prediction error is discussed and then a simple procedure for estimation of the prediction error empirically is suggested.
KeywordsNeural Network IEEE Transaction Prediction Error Radial Basis Function Fault Tolerance
Unable to display preview. Download preview PDF.
- 2.Bolt, G.: Fault tolerant in multi-layer Perceptrons. PhD Thesis, University of York, UK (1992)Google Scholar
- 4.Chiu, C.T., et al.: Modifying training algorithms for improved fault tolerance. In: ICNN 1994, vol. I, pp. 333–338 (1994)Google Scholar
- 9.Leung, C.S., Young, G.H., Sum, J., Kan, W.K.: On the regularization of forgetting recursive least square. IEEE Transactions on Neural Networks 10, 1842–1846 (1999)Google Scholar
- 10.Leung, C.S., Sum, J.: A fault tolerant regularizer for RBF networks (in submission)Google Scholar
- 11.Moody, J.E.: Note on generalization, regularization, and architecture selection in nonlinear learning systems. In: First IEEE-SP Workshop on Neural Networks for Signal Processing (1991)Google Scholar
- 16.Phatak, D.S., Tcherner, E.: Synthesis of fault tolerance neural networks. In: Proc. IJCNN 2002, pp. 1475–1480 (2002)Google Scholar
- 17.Sequin, C.H., Clay, R.D.: Fault tolerance in feedforward artificial neural networks. Neural Networks 4, 111–141 (1991)Google Scholar