An efficient multilayer quadratic perceptron for pattern classification and function approximation

We propose an architecture of a multilayer quadratic perceptron (MLQP) that combines advantages of multilayer perceptrons (MLPs) and higher-order feedforward neural networks. The features of MLQP are, in its simple structure, practical number of adjustable connection-weights and powerful learning ability. In this paper, the architecture of MLQP is described, the backpropagation learning algorithm for MLQP is derived, and the learning speed of MLQP is compared experimentally with MLP and other two kinds of the second-order feedforward neural networks on pattern classification and function approximation problems.