A Hybrid Neural Network Model for Solving Optimization Problems

Authors:
K. T. Sun;H. C. Fu
Affiliations:
-;-
Venue:
IEEE Transactions on Computers
Year:
1993

Citing 6
Cited 3

VLSI array processors

VLSI array processors
On the stability of the travelling salesman problem algorithm of Hopfield and Tank

Biological Cybernetics
A neural network approach to the 3-satisfiability problem

Journal of Parallel and Distributed Computing - Neural Computing
The logic of activation functions

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Fundamentals of Computer Alori

Fundamentals of Computer Alori

Tabu Machine: A New Neural Network Solution Approach for Combinatorial Optimization Problems

Journal of Heuristics
A Hybrid Estimator for Selectivity Estimation

IEEE Transactions on Knowledge and Data Engineering
The co-adaptive neural network approach to the Euclidean travelling salesman problem

Neural Networks

Quantified Score

Hi-index	14.99

Visualization

Abstract

A hybrid neural network model for solving optimization problems is proposed. An energy function which contains the constraints and cost criteria of an optimization problem is derived, and then the neural network is used to find the global minimum (or maximum) of the energy function, which corresponds to a solution of the optimization problem. The network contains two subnets: a constraint network and a goal network. The constraint network models the constraints of an optimization problem and computes the gradient (updating) value of each neuron such that the energy function monotonically converges to satisfy all constraints of the problem. The goal network points out the direction of convergence for finding an optimal value for the cost criteria. These two subnets ensure that the neural network finds feasible as well as optimal (or near-optimal) solutions. The traveling salesman problem and the Hamiltonian cycle problem are used to demonstrate the method.