This Article 
 Bibliographic References 
 Add to: 
A Bidirectional Associative Memory Based on Optimal Linear Associative Memory
October 1996 (vol. 45 no. 10)
pp. 1171-1179

Abstract—A new bidirectional associative memory is presented. Unlike many existing BAM algorithms, the presented BAM uses an optimal associative memory matrix in place of the standard Hebbian or quasi-correlation matrix. The optimal associative memory matrix is determined by using only simple correlation learning, requiring no pseudoinverse calculation. Guaranteed recall of all training pairs is ensured by the present BAM. The designs of a linear BAM (LBAM) and a nonlinear BAM (NBAM) are given, and the stability and other performances of the BAMs are analyzed, The introduction of a nonlinear characteristic enhances considerably the ability of the BAM to suppress the noises occurring in the output pattern, and reduces largely the spurious memories, and therefore improves greatly the recall performance of the BAM. Due to the nonsymmetry of the connection matrix of the network, the capacities of the present BAMs are far higher than that of the existing BAMs. Excellent performances of the present BAMs are shown by simulation results.

[1] T. Kohonen and M. Ruohonen, "Repesentation of Associative Pairs by Matrix Operators," IEEE Trans. Computers, vol. 22, pp. 701-702, July 1973.
[2] T. Kohonen, "Self-Organization and Associated Memory," Berlin Heidelberg. New York: Springer-Verlag, 1988.
[3] K. Matsuoka, "An Associative Network with Cross Inhibitory Connections," Biological Cybernetics, vol. 61, pp. 393-399, 1989.
[4] Z. Wnag and H. Shi, "A New Heteroassociative Memory Model with Optimal Weight Matrix," Proc. IJCNN-92, vol. II, pp. 27-30,Beijing, Nov. 1992.
[5] B. Kosko, "Adaptive Bidirectional Associative Memories," Applied Optics, vol. 26, pp. 4,947-4,860, Dec. 1987.
[6] B. Kosko, "Constructing an Associative Memory," Byte, vol. 12, pp. 137-144, Sept. 1987.
[7] B. Kosko, "Bidirectional Associative Memories," IEEE Trans. System, Man, and Cybernetics, vol. 18, pp. 49-60, Jan./Feb. 1988.
[8] M.H. Hassoun, "Dynamic Heterassociative Neural Memories," Neural Networks, vol. 2, pp. 275-287, 1988.
[9] Y.-F. Wang, J.B. Cruz Jr., and J.H. Mulligan Jr., "Two Coding Strategies for Bidirectional Associative Memory," IEEE Trans. Neural Networks, vol. 1, pp. 81-92, Mar. 1990.
[10] C.S. Leung and K.F. Cheung, "Householder Encoding for Discrete Bidirectional Associative Memory," Proc. IJCNN-91, vol. 1, pp. 237-241,Singapore, Nov. 1991.
[11] X. Zhuang, Y. Huang, and S.-S. Chen, "Better Learning for Bidirectional Associative Memory," Neural Networks, vol. 6, pp. 1,131-1,146, 1993.
[12] H. Oh and S.C. Kothari, "Adaptation of the Relaxation Method for Learning in Bidirectional Associative Memory," IEEE Trans. Neural Networks, vol. 5, pp. 576-583, July 1994.
[13] H. Kang, "Multilayer Associative Neural Network (MANNs): Storage Capacity versus Perfect Recall," IEEE Trans. Neural Networks, vol. 5, pp. 812-822, Sept. 1994.
[14] A. Albert, Regression and the Moore-Penrose Pseudoinverse.New York: Academic Press, 1972.
[15] K. Haines and R. Hecht-Nieson, "A BAM with Increased Information Storage Capacity," Proc. IEEE ICNN-88, vol. 1, pp. 181-190, July 1988.
[16] L. Personnaz, I. Guyon, and G. Dreyfus, "Information Storage and Retrieval in Spin-Glass Like Neural Networks," J. Physique Letter, vol. 46, pp. L359-365, Apr. 1985.
[17] J.A. Farrell and A.N. Michel, "A Synthesis Procedure for Hopfield's Continuous-Time Associative Memory," IEEE Trans. Circuits and Systems, vol. 37, pp. 877-884, July 1990.
[18] G.W. Stewart, Introduction to Matrix Computations.New York: Academic Press, 1976.

Index Terms:
Bidirectional associative memory, cross inhibitory connections, memory capacity, noise suppression, nonlinear function, optimal associative mapping, stability of network.
Zheng-ou Wang, "A Bidirectional Associative Memory Based on Optimal Linear Associative Memory," IEEE Transactions on Computers, vol. 45, no. 10, pp. 1171-1179, Oct. 1996, doi:10.1109/12.543710
Usage of this product signifies your acceptance of the Terms of Use.