Classification complexity and its estimation algorithm for two-class classification problem

Studies the question of H-MLP (multilayer perceptron with hardlimiting activation function) network size selection for any two-class classification problem with finite samples. Based on a concept called classification complexity (CC). Meaningful theoretical results are given. An information like criterion and an algorithm are proposed for estimating the degree of CC. This estimation process presents a constructive method to construct network structure, size, and weights configuration in each layer.