Keywords

Hopfield network, varied beam search

Abstract

This paper shows that the performance of the Hopfield network for solving optimization problems can be improved by a varied beam search algorithm. The algorithm varies the beam search size and beam intensity during the network relaxation process. It consists of two stages: increasing the beam search parameters in the flrst stage and then decreasing them in the second stage. The purpose of using such a scheme is to provide the network with a better chance to find more and better solutions. A large number of simulation results based on 200 randomly generated city distributions of the 10-city traveling salesman problem demonstrated that it is capable of increasing the percentage of valid tows by 28.3% and reducing the error rate by 40.8%, compared to the original Hopfield network.

Original Publication Citation

Zeng, X., and Martinez, T. R., "Optimization by Varied Beam Search in Hopfield Networks", Proceedings of the IEEE International Joint Conference on Neural Networks IJCNN'2, pp. 913-918, 22.