Learning multiple-valued logic networks based on backpropagation

This paper describes a learning multiple-valued logic (MVL) network based on back propagation. The learning MVL network is derived directly from a canonical realization of MVL functions and therefore its functional completeness is guaranteed. We extend traditional back propagation to include the prior human knowledge on the MVL networks, for example, the architecture and the number of hidden units and layers. The prior knowledge from the MVL canonical form can be used as initial parameters of the learning MVL network in its learning process. As a result, the prior knowledge can guide the back propagation learning process to get started from a point in the parameter space that is not far from the optimal one, thus, back propagation can fine-tune the prior knowledge for achieving a desired output. This cooperative relation between the prior knowledge and the back propagation learning process is not always present in neural networks. Simulation results are also given to confirm the effectiveness of the methods