By Topic

Solving quadratic programming problems with linear Hopfield networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Dudnikov, E. ; Int. Res. Inst. for Manage. Sci., Moscow, Russia

We consider a linear Hopfield network for solving quadratic programming problems with equation constraints. The problem is reduced to the solution of the ordinary linear differential equations with arbitrary square matrix. Because of some properties of this matrix the special methods are required for good convergence of the system. After some comparative study of neural network models for solving this problem we suggest a new model with the increased number of variables. This model is simple in implementation on the base of the linear Hopfield network and demonstrates sufficiently good convergence to the solution.

Published in:

Neural Networks, 2003. Proceedings of the International Joint Conference on  (Volume:2 )

Date of Conference:

20-24 July 2003