Theoretical considerations on the dynamics of hysteresis binary Hopfield networks for combinatorial optimization

It has been reported that hysteresis binary Hopfield networks achieve good performance for many combinatorial optimization problems. The theoretical analysis of the network dynamics or this good performance, however, is not given yet. In this paper, conditions for the convergence to an energy minimum state, and for the stability of the feasible and infeasible solutions to combinatorial optimization problems are shown in terms of the hysteresis size. Then, a theoretical explanation of the good performance of hysteresis binary Hopfield networks is also given. Simulations illustrate these theoretical conclusions.

[1]  J. Goodman,et al.  Neural networks for computation: number representations and programming complexity. , 1986, Applied optics.

[2]  Satoshi Matsuda,et al.  "Optimal" Hopfield network for combinatorial optimization with linear cost function , 1998, IEEE Trans. Neural Networks.

[3]  S. Matsuda.  Quantum neurons and their fluctuation , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[4]  Satoshi Matsuda.  "Optimal" neural representation for combinatorial optimization with linear cost function , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[5]  Lipo Wang.  Discrete-time convergence theory and updating rules for neural networks with energy functions , 1997, IEEE Trans. Neural Networks.

[6]  Yoshiyasu Takefuji,et al.  Neural network parallel computing , 1992, The Kluwer international series in engineering and computer science.

[7]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[8]  Hideaki Kikuchi,et al.  Using digital libraries as a community hall for worldwide information spiral development , 1999 .

[9]  Satoshi Matsuda,et al.  Quantized Hopfield networks for integer programming , 1999, Systems and Computers in Japan.