Improved exploration in Hopfield network state–space through parameter perturbation driven by simulated annealing

An approach is presented for treating discrete optimization problems mapped on the architecture of the Hopfield neural network. The method constitues a modification to the local minima escape (LME) algorithm which has been recently proposed as a method that uses perturbations in the network's parameter space in order to escape from local minimum states of Hopfield network. Our approach adopts this perturbation mechanism but, in addition, introduces randomness in the selection of the next local minimum state to be visited in a manner analogous with the case of Simulated Annealing. Experimental results using instances of the Weighted Maximum Independent Set problem indicate that the proposed method leads to significant improvement over the conventional LME approach in terms of quality of the obtained solutions, while requiring a comparable amount of computational effort.