Fast hopfield neural networks using subspace projections

Authors:
Daniel Calabuig;Sonia Gimenez;Jose E. Roman;Jose F. Monserrat
Affiliations:
Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain;Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain;Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain;Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain
Venue:
Neurocomputing
Year:
2010

Citing 6
Cited 0

On the stability of the travelling salesman problem algorithm of Hopfield and Tank

Biological Cybernetics
FPGA Based Implementation of a Hopfield Neural Network for Solving Constraint Satisfaction Problems

EUROMICRO '98 Proceedings of the 24th Conference on EUROMICRO - Volume 2
A continuous Hopfield network equilibrium points algorithm

Computers and Operations Research
An efficient dynamic resource allocation algorithm for packet-switched communication networks based on Hopfield neural excitation method

Neurocomputing
Neural techniques for combinatorial optimization with applications

IEEE Transactions on Neural Networks
A theoretical investigation into the performance of the Hopfield model

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Hopfield Neural Networks are well-suited to the fast solution of complex optimization problems. Their application to real problems usually requires the satisfaction of a set of linear constraints that can be incorporated with an additional violation term. Another option proposed in the literature lies in confining the search space onto the subspace of constraints in such a way that the neuron outputs always satisfy the imposed restrictions. This paper proposes a computationally efficient subspace projection method that also includes variable updating step mechanisms. Some numerical experiments are used to verify the good performance and fast convergence of the new method.