Using evolutionary programming to construct Hopfield neural networks

This paper presents a new method for constructing discrete-time Hopfield neural networks using evolutionary programming. Under constraints of fixed points, limit cycles or iteration sequences, the method simultaneously acquires both the topology and weights for Hopfield neural networks by solving inequalities. It copes with the limitations of the canonical Hopfield learning algorithm. Experimental results are presented which clearly demonstrate the effectiveness of our approach.

[1]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[2]  J. R. McDonnell,et al.  Evolving neural network connectivity , 1993, IEEE International Conference on Neural Networks.

[3]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[4]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[5]  D. B. Fogel,et al.  Using evolutionary programing to create neural networks that are capable of playing tic-tac-toe , 1993, IEEE International Conference on Neural Networks.

[6]  L. C. Stayton,et al.  On the effectiveness of crossover in simulated evolutionary optimization. , 1994, Bio Systems.

[7]  Joachim M. Buhmann,et al.  Noise-driven temporal association in neural networks , 1987 .