On problem solving with Hopfield neural networks

Summary form only given, as follows. Hopfield and Tank have shown that neural networks can be used to solve certain computationally hard problems, and in particular the traveling salesman problem (TSP). Based on network simulation results they conclude that VLSI analog neural nets can be promising in solving these problems. Recently, Wilson and Pawley presented the results of their simulations, which contradict the original results and cast doubts on the usefulness of neural nets. The authors give results of their simulations that clarify some of the discrepancies. They also investigate the scaling of TSP solutions found by neural nets as the size of the problem increases. Further, the authors consider the neural net solution of the clustering problem, also a computationally hard problem, and discuss the types of problems that appear to be well suited for a neural net approach.<>