Simulation Tests of the Optimization Method of Hopfield and Tank Using Neural Networks

摘要

The method proposed by Hopfield and Tank for using the Hopfield neural network with continuou-valued neurons to solve the traveling salesman problem (TSP) is tested by simulaton. Several researchers have apparently been unable to successfully repeat the numerical simulation documented by Hopfield and Tank. However, it appears that the reason for those difficulties is that a key parameter is reported erroneously (by four orders of magnitude) in the original paper. When a reasonable value is used for that parameter, the network performs generally as claimed Additionally, a new method of using feedback to control the input bias currents to the amplifiers is proposed and successfully tested. This eliminates the need to set the input currents by trial and error.