Neural approach for solving several types of optimization problems

Neural networks consist of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of recurrent neural networks that can be used to solve several classes of optimization problems. More specifically,...

Full description

Saved in:
Bibliographic Details
Published in:Journal of optimization theory and applications 2006-03, Vol.128 (3), p.563-580
Main Authors: DA SILVA, I. N, AMARAL, W. C, ARRUDA, L. V. R
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Bias
Combinatorial analysis
Computation
Computer engineering
Computer science
control theory
systems
Connectionism. Neural networks
Convergence
Digital signal processors
Dynamic programming
Eigenvalues
Energy
Equilibrium
Exact sciences and technology
Flows in networks. Combinatorial problems
Mathematical models
Mathematical programming
Networks
Neural networks
Nonlinearity
Operational research and scientific management
Operational research. Management science
Optimization
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks consist of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of recurrent neural networks that can be used to solve several classes of optimization problems. More specifically, a modified Hopfield network is developed and its internal parameters are computed explicitly using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent a solution of the problem considered. The problems that can be treated by the proposed approach include combinatorial optimization problems, dynamic programming problems, and nonlinear optimization problems. [PUBLICATION ABSTRACT]
ISSN:0022-3239
1573-2878
DOI:10.1007/s10957-006-9032-9