In this paper we present the implementation of Error Back Propagation Training Algorithm (EBPT) in VHSIC Hardware Descriptive Language (VHDL) platform for two standard benchmark problems of Nonlinear Classification of XOR function and Sine wave Generation. The effect of variation of learning parameters on accuracy of the output and speed of convergence of the algorithm are presented. Improved speed of convergence without much change in accuracy was obtained by incorporating Momentum method.

1. Jacek M. Zurada, “ Introduction to Aritificial Neural Networks”, Jaicob Publishing House, India 2002,ISBN 0-3 14-93391-3.
2. JiPeirong, Wang Peng , Zhao Qin, Zhao Li, “A New Parrallel Back Propagation Algorithm for Neural Networks,” IEEE International Conference on Grey Systems and Intelligent Services (GSIS), September 2011, pp. 807 -810.
3. YJ Chen, WP du Plessis, “Neural Network Implementation on FPGA”, IEEE Africon Conference 6th, Africa October 2002, vol 1.,pp 337- 342.
4. Nazeih M. Botros and M. Abdul Aziz, “Hardware Implementation of Artificial Neural Network using Field Programmable Arrays,” IEEE Conference on Industrial Electronics, December 1994, Vol 41. No.6, pp. 665-667.
5. S. Hariprasath and T.N. Prabakar, “FPGA Implementation of Multilayer Feed forward Neural Network Architecture using VHDL”, IEEE International Conference on Computing, Communication and Applications, Feb 2012, pp. 1-6.
6. John K. Kruschke and Javier R. Movellan, “Benefits of Gain: Speeded Learning and Minimal Hidden layers in Back Propagation Networks,” IEEE Transaction on Systems, Man, and Cybernetics, January/ February 1991,vol.21, No.1,pp.273- 279.
7. David E.Rumelhart, Bernard Widrow and Micheal A. Lehr, “The Basic Ideas in Neural Networks,” Communication of the ACM, vol.37,No.3, March 1994.
8. Feldman ,J.A., M.A. Fanty, and N.Goddard.1988. “Computing with structured Neural Networks,” IEEE Computer (March):91-103
9. Hopfield, J.J., and D.W. Tank. 1986 “Computing with Neural Circuits: A Model,” Science 233:625-633.
10. Lippmann, R.P. 1987. “An Introduction to Computing with Neural Nets,” IEEE Magazine on Acoustics, Signal and Speech Processing (April):4-22
11. Jacobs, R.A. 1988. ”Increased Rates of Convergence Through Learning Rate Adaption,” Neural Networks 1:295-307
12. Hripcsak, G. 1988 “Problem Solving Using Neural Networks,” San Diego, Calif.: SAIC Communications
13. Mirchandini, G., and W. Cao.1989. “On Hidden Nodes in Neural Nets”, IEEE Trans. Circuits and Systems 36(5):661-664
14. Pao, Y.H. 1989. “Adaptive Pattern Recognition and Neural Networks.” Reading Mass; Addision-Wesley Publishing Co.
15. Cybenko, G. 1990. “Complexity Theory of Neural Networks and Classification Problems,” in Neural Networks EURASIP Workshop Proc., ed. L.B. Almeida, C.J. Wellekens. Sesimbra, Portugal, February 1990, pp. 24-44
16. Funanashi, K.I. 1989. “On the Approximate Realization of Continuous Mappings by Neural Networks,” Neural Networks 2:183-192.
17. Karin, E.D. 1990. “A Simple Procedure for Pruning Back-Propagation Trained Neural Networks,” IEEE Trans. On Neural Networks 1(2): 239-242.
18. White, H. 1989. “Learning in Artificial Neural Networks: A Statistical Perspective,” Neural Computation 1(4);425-469
19. Wieland, A., and R. Leighton. 1988. “Geometric Analysis of Neural Networks Capabilities,” MP-88 W 00022. McLean, Va.: Mitre Corporation.
20. Poggio, T. and F. Girosi. 1990. “Networks for Approximation and Learning” Proc. IEEE 78(9): 1481-1497.

Error Back Propagation Training VHDL Momentum Method