Abstract
This paper first derives the training objective function of faulty radial basis function (RBF) networks, in which open weight fault and multiplicative weight noise co-exist. A regularizer is then identified from the objective function. Finally, the corresponding learning algorithm is developed. Compared to the conventional approach, our approach has a better fault tolerant ability. We then develop a faulty mean prediction error (FMPE) formula to estimate the generalization ability of faulty RBF networks. The FMPE formula helps us to understand the generalization ability of faulty networks without using a test set or generating a number of potential faulty networks. We then demonstrate how to use our FMPE formula to optimize the RBF width for the co-existing fault situation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chiu, C.T., Mehrotra, K., Mohan, C.K., Ranka, S.: Modifying training algorithms for improved fault tolerance. In: Proceedings of the International Conference on Neural Networks 1994, vol. 4, pp. 333–338 (1994)
Leung, C.S., Sum, J.: A fault-tolerant regularizer for RBF networks. IEEE Trans. Neural Netw. 19(3), 493–507 (2008)
Zhou, Z.H., Chen, S.F.: Evolving fault-tolerant neural networks. Neural Computing and Applications 11(3-4), 156–160 (2003)
Burr, J.: Digital neural network implementations. In: Neural Networks, Concepts, Applications, and Implementations, vol. III, pp. 237–285. Prentice-Hall, Englewood Cliffs (1995)
Bolt, G.: Fault Tolerant Multi-Layer Perceptron Networks. PhD thesis, Department of Computer Science, University of York, UK (July 1992)
Simon, D., El-Sherief, H.: Fault-tolerance training for optimal interpolative nets. IEEE Trans. on Neural Netw. 6, 1531–1535 (1995)
Phatak, D.S., Tchernev, E.: Synthesis of fault tolerant neural networks. In: Proc. IJCNN 2002, pp. 1475–1480 (2002)
Moody, J.E.: Note on generalization, regularization, and architecture selection in nonlinear learning systems. In: Proc. First IEEE-SP Workshop on Neural Networks for Signal Processing, pp. 1–10 (1991)
Leung, C.S., Tsoi, A.C., Chan, L.W.: Two regularizers for recursive least square algorithms in feedforward multilayered neural networks. IEEE Trans. Neural Netw. 12(6), 1314–1332 (2001)
Fedorov, V.V.: Theory of optimal experiments. Academic Press (1972)
Narendra, K.S., Parthasarathy, K.: Neural networks and dynamical systems. International Journal of Approximate Reasoning 6(2), 109–131 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, CS., Sum, J.PF. (2011). Regularizer for Co-existing of Open Weight Fault and Multiplicative Weight Noise. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24965-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-24965-5_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24964-8
Online ISBN: 978-3-642-24965-5
eBook Packages: Computer ScienceComputer Science (R0)