A neural network shortest path algorithm

This paper develops a neural network implementation of a shortest path algorithm using a Hopfield network architecture. The main advantage of this neural network is that the number of neurons in the network grows linearly with the number of links in the graph instead of growing with the square of the number of nodes in the graph, as is the case with existing algorithms. The properties of this neural network are then investigated and its performance is evaluated through an extensive simulation study.<<ETX>>