Multilayered feed-forward neural networks are considered universal approximators and hence extensively been used for function approximation. Function approximation is an instance of supervised learning which is one of the most studied topics in machine learning, artificial neural networks, pattern recognition, and statistical curve fitting. Bidirectional associative memory is another class of networks which has been used for approximating various functions. In the present study, an approach for using MLFNN architectures as BAM with BP learning has been proposed and initially been tested on certain functions. The results obtained are analyzed and presented.

1. Rumelhan D. E. , Hinton G. E. , and Williams R. J. , Learning Internal Representations by Error Propagation, Parallel Distributed Processing, Vol. I Foundations, MIT Press, Cambridge, MA, pages 318-364. 1986.
2. Tang C. Z. and Kwan H. K. , Parameter effects on convergence speed and generalization capability of back-propagation algorithm International Journal of Electronics, 74(1): 35-46, January 1993.
3. Kosko B. , Neural Networks and Fuzzy Systems (Prentice-Hall. Inc. , New Jersey, 1992)
4. Pearlmutter B. A. , Gradient calculations for dynamic recurrent neural networks: a survey. IEEE Trans. On Neural Networks, 6 (5):1212-1228, Sept. 1995
5. Prokhorov D. V. , Feldkamp L. A. , and Tyukin I. Y. , Adaptive behavior with fixed weights in RNN: an overview. Proceedings of International Joint Conference on Neural Networks, 2002, pages 201 8-2022
6. Kwan H. K. and Yan J. , Second-order recurrent neural network for word sequence learning, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong, May 2-4. 2001, pages 405-408.
7. Tai H. -M. . Wu C. -H. , and Jong, T. -L. , High-order bidirectional associative memor': Elecrronics krlers, 25(21):1424-1425, 12th Oct. 1989.
8. Jeng Y. -J. , Yeh C. -C. , and Chiueh T. D. , 'Exponential bidirectional associative memories", Electronics Letters, 26(11):717-718,24th May1990.
9. Wang T. . Zhuang X. , and Xing X. , 'Weight learning of bidirectional associative memories by global minimization", IEEE Trans. on Neural Networks, 3(6):1010-1018, Nov. 1992.
10. Wang Y. F. , Cruz J. B. and Mulligan J. H. , "Two coding strategies for bidirectional associative memory", IEEE Trans. Neural Networks, vol. 1, no. 1, pp 81-92, 1990
11. Wang Y. F. , Cruz J. B. and Mulligan J. H. , "Guaranteed recall of all training pairs for bidirectional associative memory", IEEE Trans. Neural Networks, vol. 2, no. 6, pp 559-567, 1991
12. Kang H. , "Multilayer associative neural network (MANN's): Storage capacity versus perfect recall", IEEE Trans. Neural Networks, vol. 5, pp 812-822, 1994
13. Wang Z. , "A bidirectional associative memory based on optimal linear associative memory", IEEE Trans. Neural Networks, vol. 45, pp 1171-1179, Oct. 1996
14. Hassoun M. H. and Youssef A. M. , "A high performance recording algorithm for Hopfield model associative memories", Opt. Eng. , vol. 27, no. , pp 46-54, 1989
15. Simpson P. K. , "Higher-ordered and interconnected bidirectional associative memories", IEEE Trans. Syst. Man. Cybern. , vol. 20, no. 3, pp 637-652, 1990
16. Zhuang X. , Huang Y. and Chen S. S. , "Better learning for bidirectional associative memory", Neural Networks, vol. 6, no. 8, pp1131-1146, 1993
17. Oh H. and Kothari S. C. , "Adaptation of the relaxation method for learning bidirectional associative memory", IEEE Trans. Neural Networks, vol. 5, pp 573-583, July 1994
18. Wang C. C. and Don H. S. , "An analysis of high-capacity discrete exponential BAM", IEEE Trans. Neural Networks, vol. 6, no. 2, pp 492-496, 1995

Neural Networks Multilayered Feed-forward Neural Network (mlfnn) Bidirectional Associative Memory (bam) Function Approximation