This Article 
 Bibliographic References 
 Add to: 
A Neuron-Weighted Learning Algorithm and its Hardware Implementation in Associative Memories
May 1993 (vol. 42 no. 5)
pp. 636-640

A novel learning algorithm for a neuron-weighted associative memory (NWAM) is presented. The learning procedure is cast as a global minimization, solved by a gradient descent rule. An analog neural network for implementing the learning method is described. Some computer simulation experiments are reported.

[1] L. F. Abbott and T. B. Kepler, "Optimal learning in neural network memories,"J. Phys. A: Math. Gen., vol. 22, pp. L711-717, 1989.
[2] J. Bruck and V. P. Roychowdhury, "On the number of spurious memories in the Hopfield model,"IEEE Trans. Inform. Theory, vol. IT-36, no. 2, pp. 393-397, 1990.
[3] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities,"Proc. Nat. Acad. Sci. USA, vol. 79, 1982, pp. 2554-2558.
[4] M. P. Kennedy and L. O. Chua, "Neural networks for nonlinear programming,"IEEE Trans. Circuits Syst., vol. 35, no. 5, pp. 554-562, 1988.
[5] W. Krauth and M. Mezard, "Learning algorithms with optimal stability in neural networks,"J. Phys. A: Math. Gen., vol. 20, pp. L745-752, 1987.
[6] R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, "The capacity of the Hopfield associative memory,"IEEE Trans. Inform. Theory, vol. IT-33, pp. 461-482, 1987.
[7] A. Moopenn, J. Lambe, and A. P. Thankoor, "Electronic implementation of associative memory based on neural network models,"IEEE Trans. Syst., Man., Cybern., vol. SMC-17, no. 2, pp. 325-331, 1987.
[8] G. V. Vanderplaats,Numerical Optimization Techniques for Engineering Design: With Applications. New York: McGraw-Hill, 1984.
[9] A. R. Vazquez, R. D. Castro, A. Rueda, J. L. Huertas, and E. S. Sinencio, "Nonlinear switched-capacitor neural networks for optimization problems,"IEEE Trans. Circuits Syst., vol. 37, no. 3, pp. 384-397, 1990.
[10] C. F. Zhang, X. Q. Wang, Z. Q. Zhou, and K. H. Zhao, "Analysis of varieties of neural network models for associative memory,"J. Pattern Recognition Artif. Intell. China, vol. 3, no. 1, pp. 21-27, 1990.

Index Terms:
hardware implementation; associative memories; learning algorithm; neuron-weighted associative memory; NWAM; global minimization; gradient descent rule; analog neural network; computer simulation experiments; content-addressable storage; learning (artificial intelligence); neural chips; neural nets.
Tao Wang, Xinhau Zhuang, XiaoLiang Xing, Xipeng Xiao, "A Neuron-Weighted Learning Algorithm and its Hardware Implementation in Associative Memories," IEEE Transactions on Computers, vol. 42, no. 5, pp. 636-640, May 1993, doi:10.1109/12.223686
Usage of this product signifies your acceptance of the Terms of Use.