Radial basis perceptron network and its applications for pattern recognition

Based on radial basis function neural network (RBFN) and perceptron neural network, a new four-layer feed-forward neural network named radial basis perceptron network (RBPN) is presented in this paper. This network can be summarized as follows: (1) It is not fully connected but uses selective connection between the units of two hidden layers; (2) During the learning procedure, RBPN adopts an input-output clustering (IOC) method to define the number of units of hidden layers and select centers; (3) The width parameter a of centers is self-adjustable according to the information included in the learning samples. The effectiveness of this network is illustrated using an example taken from applications for component analysis of civil building materials. Simulation shows that RBPN can be used to predict the components of civil building materials successfully and gets good generalization ability