On the stability of the travelling salesman problem algorithm of Hopfield and Tank
Biological Cybernetics
“Teachers and classes” with neural networks
International Journal of Neural Systems
A theoretical investigation into the performance of the Hopfield model
IEEE Transactions on Neural Networks
Convergence properties of the softassign quadratic assignment algorithm
Neural Computation
Parameter setting of the Hopfield network applied to TSP
Neural Networks
Goal Sequencing for Construction Agents in a Simulated Environment
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Design and analysis of an efficient neural network model for solving nonlinear optimization problems
International Journal of Systems Science
A novel optimizing network architecture with applications
Neural Computation
Neural Computation
Implementing soft computing techniques to solve economic dispatch problem in power systems
Expert Systems with Applications: An International Journal
Stability and convergence analysis of a neural model applied in nonlinear systems optimization
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
The continuous hopfield networks (CHN) for the placement of the electronic circuits problem
WSEAS Transactions on Computers
A study of the transiently chaotic neural network for combinatorial optimization
Mathematical and Computer Modelling: An International Journal
| Hi-index | 0.00 |
There has recently been much research interest in the use of feedback neural networks to solve combinatorial optimization problems. Although initial results were disappointing, it has since been demonstrated how modified network dynamics and better problem mapping can greatly improve the solution quality. The aim of this paper is to build on this progress by presenting a new analytical framework in which problem mappings can be evaluated without recourse to purely experimental means. A linearized analysis of the Hopfield network's dynamics forms the main theory of the paper, followed by a series of experiments in which some problem mappings are investigated in the context of these dynamics. The experimental results are seen to be compatible with the linearized theory, and observed weaknesses in the mappings are fully explained within the framework. What emerges is a largely analytical technique for evaluating candidate problem mappings, without recourse to the more usual trial and error.