This work focuses on improving the Hopfield network for solving optimization problems. Although much work has been done in this area, the performance of the Hopfield network is still not satisfactory in terms of valid convergence and quality of solutions. We address this issue by combing a new activation function (EBA) and a new relaxation procedure (CR) in order to improve the performance of the Hopfield network. Each of EBA and CR has been individually demonstrated capable of substantially improving the performance. The combined approach has been evaluated through 20,000 simulations based on 200 randomly generated city distributions of the 10-city traveling salesman problem. The result shows that combining the two methods is able to further improve the performance. Compared to CR without combining with EBA, the combined approach increases the percentage of valid tours by 21.0% and decreases the error rate by 46.4%. As compared to the original Hopfield method, the combined approach increases the percentage of valid tours by 245.7% and decreases the error rate by 64.1%.
[1]
Sanjit K. Mitra,et al.
Alternative networks for solving the traveling salesman problem and the list-matching problem
,
1988,
IEEE 1988 International Conference on Neural Networks.
[2]
Barry Cooper.
Higher order neural networks-Can they help us optimise?
,
1995
.
[3]
Vincenzo Catania,et al.
Tuning Hopfield neural network by a fuzzy approach
,
1996,
Proceedings of International Conference on Neural Networks (ICNN'96).
[4]
Stan Z. Li,et al.
Improving convergence and solution quality of Hopfield-type neural networks with augmented Lagrange multipliers
,
1996,
IEEE Trans. Neural Networks.
[5]
Tony R. Martinez,et al.
A New Activation Function in the Hopfield Network for Solving Optimization Problems
,
1999,
ICANNGA.
[6]
Mahesan Niranjan,et al.
A theoretical investigation into the performance of the Hopfield model
,
1990,
IEEE Trans. Neural Networks.