Note: [1] This is the extended version of the paper: W.H. Schuler, C.J. Bastos-Filho and A.L. Oliveira, “A Novel Hybrid Training Method for Hopfield Neural Networks Applied to Routing in Communications Networks,” in Proc. 7th international Conference on Hybrid intelligent Systems (HIS 2007), pp. 36–41, 17–19 Sept. 2007.
Abstract: Efficient routing algorithms are very important for the operation of communication networks, including the Internet. This article presents a hybrid intelligent method for routing which combines Hopfield Neural Networks (HNN) and simulated annealing (SA). The proposed method introduces a modified version of the discrete-time equation used to calculate the new neuron input. The novel version of the equation aims to improve the HNN convergence, thereby decreasing the computation cost. In our method, the SA algorithm is used to obtain the optimal parameters of the HNN. Simulations reported in this paper show that the proposed method outperforms previous approaches, by computing routes using smaller number of iterations and smaller error.
Keywords: Hopfield neural network, communication network, shortest path, simulated annealing
