DESIGN OF COMPETITION-BASED NEURAL NETWORKS FOR COMBINATORIAL OPTIMIZATION

Abstract

A systematic approach to the design of neural networks for combinatorial optimization is presented in this paper. This approach adopts a methodology which is based on competition. The neural networks for optimization problem solving are connected using the competitive geometry. Our approach relies on the use of simple heuristics in network design. It is therefore easy to learn. The performance of such networks is also impressive. Two examples are also included in this paper to demonstrate our approach and to present results of performance study.