Construct The Structure of Stochastic Multilayer Perceptron Using The Model Search Method

The author gives an algorithm to search the structure of a stochastic models with hidden variable. The author have shown the algorithm to nd the hidden structure of the Hidden Markov Model and in this article, the algorithm is applied for one of the other stochastic models which have hidden probabilistic variables. I. Introduction The Neural Networks have great ability to express various types of functions. The Neural Network has this ability because it has a lot of parameters and also because it can have many kinds of structures which is determined by the number of the cells and the connections between them. Conversely speaking, if we want to use the Neural Network as a powerful tool, it is important to set these parameters and also determine the structure correctly. To set the values of the parameters, we have some algorithms. Though, we do not have any successful algorithm to choose the structures of the Networks except trial and error. The problem to determine the structures of..