Dynamic programming with neural networks

The primary objective of dynamic programming is to reduce the solution of a complex optimization problem to a sequence of simpler ones. This paper discusses the alternatives available for solving a class of dynamic programming problems using neural networks. The specific focus is upon graphical shortest path problems where the objective is to discover the least cost path in a weighted graph between a given source vertex and one or more destinations. This problem class has numerous practical applications including data network touring and speech recognition. Various neural network based approaches to this problem class are discussed and contrasted