Improving the Hopfield network through beam search

Author

Zeng, Xinchuan ; Martinez, Tony R.

Author_Institution

Dept. of Comput. Sci., Brigham Young Univ., Provo, UT, USA

Volume

2

fYear

2001

fDate

2001

Firstpage

1162

Abstract

We propose a beam search mechanism to improve the performance of the Hopfield network for solving optimization problems. The beam search re-adjusts the top M (M>1) activated neurons to more similar activation levels in the early phase of relaxation, so that the network has the opportunity to explore more alternative, potentially better solutions. We evaluated this approach using a large number of simulations (20,000 for each parameter setting), based on 200 randomly generated city distributions of the 10-city travelling salesman problem. The results show that the beam search has the capability of significantly improving the network performance over the original Hopfield network, increasing the percentage of valid tours by 17.0% and reducing error rate by 24.3%

Keywords

Hopfield neural nets; relaxation theory; search problems; travelling salesman problems; Hopfield neural network; beam search; optimization; relaxation; travelling salesman problem; Cities and towns; Computer science; Error analysis; Hopfield neural networks; Network topology; Neural networks; Neurons; Random number generation; Testing; Traveling salesman problems;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-7044-9

Type

conf

DOI

10.1109/IJCNN.2001.939525

Filename

939525