Neural Network for Shortest Path Problems Accelerated with Parallel Multi-core Architecture

Abstract

A Pulse-Coupled Artificial Neural Network capable of efficiently tackle the problem of finding the shortest path between two nodes is presented. Once the Artificial Network finds the target node at minimum cost, an extraction or Knowledge Explicitation of this Network is performed to recover the final trajectory. The efficient solution of the shortest path problem has applications in such important and current areas as robotics, telecommunications, operation research, game theory, computer networks, internet, industrial design, transport phenomena, design of electronic circuits and others, so it is a subject of great interest in the area of combinatorial optimization. Due to the parallel design of the Neuronal Network presented here, it is possible speed up the solution using parallel multi-processors; this solution approach can be highly competitive, as observed from the good results obtained, even in cases with thousands of nodes.