Tuning Hopfield Neural Network by a Fuzzy Approach

Solution of NP-hard optimization problems by Hopfield Neural Network requires the determination of coefficients linked to the surrounding conditions of the optimization problem itself. Actually, this is a time-consuming task. The aim of the paper is to propose an automatic strategy for determining the coefficients of a Hopfield network. The strategy proposed can be applied to any optimization problem and is based on the determination of a set of fuzzy inferences which vary the coefficients until values which guarantee the quality of the neural solution are reached.