A novel hybrid training method for hopfield neural networks applied to routing in communications networks

Authors:
W. H. Schuler;C. J. A. Bastos-Filho;A. L. I. Oliveira
Affiliations:
(Correspd. E-mails: whs@dsc.upe.br) Department of Computing Systems, Univesity of Pernambuco, Recife, PE, Brazil;Department of Computing Systems, Univesity of Pernambuco, Recife, PE, Brazil;Department of Computing Systems, Univesity of Pernambuco, Recife, PE, Brazil
Venue:
International Journal of Hybrid Intelligent Systems
Year:
2009

Citing 3
Cited 1

Routing in telecommunications networks with ant-like agents

IATA '98 Proceedings of the second international workshop on Intelligent agents for telecommunication applications
Dynamic RWA Based on the Combination of Mobile Agents Technique and Genetic Algorithms in WDM Networks with Sparse Wavelength Conversion

IEICE - Transactions on Information and Systems
AntNet: distributed stigmergetic control for communications networks

Journal of Artificial Intelligence Research

Fuzzy modeling of digital products pricing in the virtual marketplace

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

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.