Abstract
Recently, some stochastic neural network models have been proposed for the purpose of overcoming the defect that the deterministic neural network models do not have the ability of escaping from a local optimum solution. However, the setting of various system parameters for these stochastic neural network models is more complicated than it for the deterministic neural network models. In this paper, a new stochastic neural network model is suggested in order to reduce the complication of setting the system parameters. For practical purposes, the proposed model is applied to the problem of grouping parts and tools in FMS.
