Using the general energy function of the random neural networks to solve the graph partitioning problem

Abstract:

Typically, the neural networks are used to provide heuristic solutions to very difficult optimization problems. This is usually achieved by designing neural networks whose energy function mimics a cost function which embodies the optimization problem to be solved. In this paper, we propose to use a general energy function of the random neural network, defined in previous work, to solve the graph partitioning problem. We show as this energy function permits to define a general method to use the random neural network in the resolution of combinatorial optimization problems.

Año de publicación:

1996

Keywords:

Fuente:

scopus