Abstract
This paper presents a technique for improving the fault tolerance capability of Artificial Neural Networks. This characteristic of distributed systems, which is usually pointed out as one of the advantages of this structure hasn’t been deeply studied and can be improved in most of the networks. The solution implemented here consists of changing the architecture of feedforward artificial neural networks after the training stage while maintaining its output unchanged. It involves evaluating the elements of the Artificial Neural Network which are more sensible to a fault and duplicating inputs, bias, weights or neurons, according to the evaluation done before. This solution is very interesting because it allows maintaining the pre-trained network, but its cost is the need of additional hardware resources to implement the same network. The paper also presents an example of the application of the technique to illustrate its effectiveness.
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
Cavalieri, S., Mirabella, O.: A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks. Neural Networks 12, 91–106 (1999)
Elsimary, H., Mashali, S., Shaheen, S.: Performance evaluation of a novel fault tolerance training algorithm. In: Proceedings of the World congress on computational intelligence, vol. 2, pp. 856–860 (1994)
Elsimary, H., Mashali, S., Shaheen, S.: Generalization ability of fault tolerant feed forward neural nets. In: Proceedings of the IEEE International conference on systems, man and cybernetics, vol. 1, pp. 30–34 (1995)
Parker, K.: The Boundary Scan Handbook (1992)
Bolt, G.: Investigating the Fault Tolerance in Artificial Neural Networks., Technical Report YCS 154 from the University of York, available at the internet (1991)
Eickhoff, R., Rückert, U.: Tolerance of Radial Basis Functions Against Stuck-at-Faults. In: International Conference of Artificial Neural Networks, Poland, pp. 1003–1008 (2005)
Phatak, D.S.: Complete and Partial Fault Tolerance of Feedforward Neural Nets. IEEE Transactions on Neural Networks 6/2, 446–456 (1995)
Tchernev, E.B., Phatak, D.S.: Investigating the Fault Tolerance of Neural Networks, NCA (2005)
Dias, F.M., Antunes, A.: Fault tolerance of feedforward neural networks: an open discussion for a global Model. Engineering Applications of Artificial Intelligence (submitted, 2007)
Dias, F.M., Antunes, A., Mota, A.: Artificial Neural Networks: a Review of Commercial Hardware. Engineering Applications of Artificial Intelligence, IFAC 17/8, 945–952 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dias, F.M., Antunes, A. (2008). Fault Tolerance Improvement through Architecture Change in Artificial Neural Networks. In: Kang, L., Cai, Z., Yan, X., Liu, Y. (eds) Advances in Computation and Intelligence. ISICA 2008. Lecture Notes in Computer Science, vol 5370. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92137-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-92137-0_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92136-3
Online ISBN: 978-3-540-92137-0
eBook Packages: Computer ScienceComputer Science (R0)