Abstract
This paper studies fault-tolerance problem of feedforward neural networks implemented in pattern recognition. Based on dynamical system theory, two concepts of pseudo-attractor and its region of attraction are introduced. A method estimating fault tolerance of feedforward neural networks has been developed. This paper also presents definitions of terminologies and detailed derivations of the methodology. Some preliminary results of case studies using the proposed method are shown, the proposed method has provided a framework and an efficient way for direct evaluation of fault-tolerance in feedforward neural networks.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Haykin, S.: Neural Network-A comprehensive Foundation. Prentice-Hall, Englewood Cliffs (1994)
Hao, P., Xiao, W., et al.: Investigation of structure Variation of BP Network. Control and Decision 16, 287–298 (2001)
Atiya, A., Ji, C.: How initial conditions affect generalization performance in large networks. IEEE Trans. on Neural Networks 8, 448–451 (1997)
Kwak, N., Choi, C.H.: Input feature selection for classification problems. IEEE Trans. on Neural Networks 13, 143–159 (2002)
Back, A.D., Trappenberg, T.P.: Selecting inputs for modeling using normalized higher order statistics and independent component analysis. IEEE Trans. on Neural Networks 12, 612–617 (2001)
Ywung, D.Y.: Constructive neural network as estimators of bayesian discriminant Function. Pattern Recognition 26, 189–204 (1993)
Mcinerney, M., Dhawan, A.P.: Use of genetic algorithm with back propagation in train ing of feedforward neural networks (Published Conference Proceedings style). In: 1993 IEEE Int. Conf. Neural Networks, San Francisco, pp. 203–208 (1993)
Zhang, F., Zhao, G.: Some issues about neural networks of associative memory. Automation 20, 513–521 (1994)
Liu, J.L., Yang, Z.S., Zeng, S.B.: Foundation tutorial of engineering mathematics (Book style). Tianjin University Press (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jiang, H., Liu, T., Wang, M. (2006). Direct Estimation of Fault Tolerance of Feedforward Neural Networks in Pattern Recognition. In: King, I., Wang, J., Chan, LW., Wang, D. (eds) Neural Information Processing. ICONIP 2006. Lecture Notes in Computer Science, vol 4233. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11893257_14
Download citation
DOI: https://doi.org/10.1007/11893257_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46481-5
Online ISBN: 978-3-540-46482-2
eBook Packages: Computer ScienceComputer Science (R0)