CBP networks as a generalized neural model

This paper analyzes the circular backpropagation network, a simple modification of the multilayer perceptron with interesting practical properties, especially well-suited to cope with pattern classification tasks. The proposed model unifies the two main representation paradigms found in the class of mapping networks for classification, namely, the surface-based and the prototype-based schemes, while retaining the advantage of being trainable by back-propagation. Multilayer perceptrons, radial-basis-function networks and vector-quantization networks are shown to be implementable with small modifications to the model under study.