A neuro-evolutionary approach to produce general hyper-heuristics for the dynamic variable ordering in hard binary constraint satisfaction problems

Abstract

This paper introduces a neuro-evolutionary approach to produce hyper-heuristics for the dynamic variable ordering for hard binary constraint satisfaction problems. The model uses a GA to evolve a population of neural networks architectures and parameters. For every cycle in the GA process, the new networks are trained using backpropagation. When the process is over, the best trained individual in the last population of neural networks represents the general hyper-heuristic.