A two phase method for determining the number of neurons in the hidden layer of a 3-layer neural network

In general the number of neurons in the hidden layer of multi-layer neural network is determined by trial and error of researchers. There is also an information criteria to determine the number of neurons in the hidden layer. In this paper, we propose a two-phase method to determine the optimal number of neurons in the hidden layer of a 3-layer neural network. In the first phase, candidates of the number of neurons in the hidden layer are determined by using the back-propagation method. In the second phase, the optimal number of neurons is determined by considering the generalization capacity. It is found from the prediction results that the two phase method for determining the number of neurons in the hidden layer is superior to the decision method of trial and error of researchers. In addition, since the number of neurons in the hidden layer can be determined in a short time, it is thought that the proposed method is effective.