A derivative of the Hopfield-Tank neural network model thatreliably solves the traveling salesman problem

摘要

Summary form only given. The authors investigated the suitabilitynof the Hopfield-Tank neural network model for solving several constraintnsatisfaction problems. They started by attempting to reproduce thenresults of Hopfield and Tank, who claim to have built a neural networknthat finds good solutions to the traveling salesman problem (TSP). Theynfound this very difficult. They describe the Hopfield-Tank neuralnnetwork model (HTD) and how it is used to solve the TSP. They describentheir derivation of the HTD. The authors give a number of parameters innthe HTD whose values are critical to the successful operation of thennetwork, and discuss the heuristics used to find the proper values fornthese parameters. The authors then present test results for the HTD thatnindicate that it reliably yields good solutions for the TSP