论文信息 - A Positively Self-Feedbacked Hopfield Neural Network for N-Queens Problem

A Positively Self-Feedbacked Hopfield Neural Network for N-Queens Problem

Abstract. In this paper, a binary Hopfield neural network with positive selffeedbacks and its collective computational properties are studied. It is proved theoretically and confirmed by simulating the randomly generated Hopfield neural networks with positive self-feedbacks that the emergent collective properties of the original Hopfield neural network also are present in the Hopfield network with positive self-feedbacks. As an example, the network is also applied to the N-Queens problem and results of computer simulations are presented and used to illustrate the computation power of the networks.

[1] Tetsuro Kakeshita,et al. Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network , 1997 .

[2] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[3] Teruo Higashino,et al. A Proposal of Neuron Filter: A Constraint Resolution Scheme of Neural Networks for Combinatorial Optimization Problems , 2000 .

[4] J. Hopfield,et al. Computing with neural circuits: a model. , 1986, Science.

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

[6] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

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

[8] 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.