Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Neural network models for Linear Programming

Conference ·
OSTI ID:5347615

The purpose of this paper is to present a neural network that solves the general Linear Programming (LP) problem. In the first part, we recall Hopfield and Tank's circuit for LP and show that although it converges to stable states, it does not, in general, yield admissible solutions. This is due to the penalization treatment of the constraints. In the second part, we propose an approach based on Lagragrange multipliers that converges to primal and dual admissible solutions. We also show that the duality gap (measuring the optimality) can be rendered, in principle, as small as needed. 11 refs.

Research Organization:
Oak Ridge National Lab., TN (USA)
Sponsoring Organization:
DOE/ER
DOE Contract Number:
AC05-84OR21400
OSTI ID:
5347615
Report Number(s):
CONF-900116-2; ON: DE89015974; CNN: DARPA1868-A037-A1
Country of Publication:
United States
Language:
English