Optimization neural net for multiple-target data association: real-time optical lab results

摘要

The Hopfield neural network was first used for optimization in solving the famous Traveling Salesman Problem. A similar approach has been applied to the solution of another problem, namely, data association for multiple targets. Simulation data are presented which demonstrate the network's ability to successfully determine the optimum data association solutions, with target noise present. Simulations also indicate the ability to solve the problem on a low accuracy (analog optical) processor. Optical implementation issues are discussed, and an optical architecture is presented with laboratory results.