Abstract
In neural networks, network faults can be exhibited in different forms, such as node fault and weight fault. One kind of weight faults is due to the hardware or software precision. This kind of weight faults can be modelled as multiplicative weight noise. This paper analyzes the capacity of a bidirectional associative memory (BAM) affected by multiplicative weight noise. Assuming that weights are corrupted by multiplicative noise, we study how many number of pattern pairs can be stored as fixed points. Since capacity is not meaningful without considering the error correction capability, we also present the capacity of a BAM with multiplicative noise when there are some errors in the input pattern. Simulation results have been carried out to confirm our derivations.
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
Kohonen, T.: Correlation matrix memories. IEEE Transaction Computer 21, 353–359 (1972)
Palm, G.: On associative memory. Biolog. Cybern. 36, 19–31 (1980)
Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst. Man, and Cybern. 18, 49–60 (1988)
Leung, C.S.: Encoding method for bidirectional associative memory using projection on convex sets. IEEE Trans. Neural Networks 4, 879–991 (1993)
Leung, C.S.: Optimum learning for bidirectional associative memory in the sense of capacity. IEEE Trans. Syst. Man, and Cybern. 24, 791–796 (1994)
Wang, Y.F., Cruz, J.B., Mulligan, J.H.: Two coding strategies for bidirectional associative memory. IEEE Trans. Neural Networks 1, 81–92 (1990)
Lenze, B.: Improving leung’s bidirectional learning rule for associative memories. IEEE Trans. Neural Networks 12, 1222–1226 (2001)
Shen, D., Cruz, J.B.: Encoding strategy for maximum noise tolerance bidirectional associative memory. IEEE Trans. Neural Networks 16, 293–300 (2005)
Leung, C.S., Chan, L.W.: The behavior of forgetting learning in bidirectional associative memory. Neural Computation 9, 385–401 (1997)
Leung, C.S., Chan, L.W., Lai, E.: Stability and statistical properties of second-order bidirectional associative memory. IEEE Transactions on Neural Networks 8, 267–277 (1997)
Wang, B.H., Vachtsevanos, G.: Storage capacity of bidirectional associative memories. In: Proc. IJCNN 1991, Singapore, pp. 1831–1836 (1991)
Haines, K., Hecht-Nielsen, R.: A bam with increased information storage capacity. In: Proc. of the 1988 IEEE Int. Conf. on Neural Networks, pp. 181–190 (1988)
Amari, S.: Statistical neurodynamics of various versions of correlation associative memory. In: Proc. of the 1988 IEEE Int. Conf. on Neural Networks, pp. 181–190 (1988)
Burr, J.: Digital neural network implementations. In: Neural Networks, Concepts, Applications, and Implementations, vol. III, Prentice Hall, Englewood Cliffs, New Jersey (1991)
Holt, J., Hwang, J.-N.: Finite precision error analysis of neural network hardware implementations. IEEE Transactions on Computers 42(3), 281–290 (1993)
Lam, P.M., Leung, C.S., Wong, T.T.: Noise-resistant fitting for spherical harmonics. IEEE Transactions on Visualization and Computer Graphics 12(2), 254–265 (2006)
Bernier, J.L., Ortega, J., Rodriguez, M.M., Rojas, I., Prieto, A.: An accurate measure for multilayer perceptron tolerance to weight deviations. Neural Processing Letters 10(2), 121–130 (1999)
Bernier, J.L., Diaz, A.F., Fernandez, F.J., Canas, A., Gonzalez, J., Martin-Smith, P., Ortega, J.: Assessing the noise immunity and generalization of radial basis function networks. Neural Processing Letters 18(1), 35–48 (2003)
Sripad, A., Snyder, D.: Quantization errors in floating-point arithmetic. IEEE Transactions on Speech, and Signal Processing 26, 456–463 (1978)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, C.S., Sum, P.F., Wong, TT. (2008). Analysis on Bidirectional Associative Memories with Multiplicative Weight Noise. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)