Solving search problems with subgoals using an artificial neural network

Search problems with a series of subgoals can be solved using symbolic search algorithms. A method is proposed to use a neural network to perform this type of search by translating the serial and temporal resolution path into a spatial and parallel constraint structure using both state units and constraint units. A network is designed for the Missionaries and Cannibals Problem to illustrate the method. It is proved that every stable state of the neural network is definitely a feasible solution to the problem. The network finds the solution using a parallel stochastic relaxation algorithm. Computer simulation results are presented