A Learning Multiple-Valued Logic Network that can Explain Reasoning

Abstract

This paper describes a learning multiple-valued logic (MVL) network that can explain reasoning. The learning MVL network is derived directly from a canonical realization of MVL functions and therefore its functional completeness is guaranteed. We develop traditional back-propagation to the MVL networks and drive a specific algorithm for the MVL networks. The algorithm combines back-propagation learning with other features of MVL networks, including the prior human knowledge on the MVL networks, for example, the rchitecture, the number of hidden units and layers, and many other useful parameters for the networks. 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 easily. This cooperative relation between the prior knowledge and the back-propagation learning process is not always present in neural networks. The learning process in the MVL network also shares some cytology behaviors, in particular the cell adhesion, the cell aptopsis (the death of cell), and the cluster cell aptopsis (the death of cluster cells), and presents these properties in the artificial MVL network successfully. Simulation results are also given to confirm the effectiveness of the methods.

A Chaotic Clonal Selection Algorithm and its Application to Synthesize Multiple‐Valued Logic Functions

“…However, during learning, many nodes and parameters such as weights and thresholds were usually necessary to approximate an MVL function and any knowledge which was available prior to training was unable to be used. Compared with the BP algorithms, the LS methods have easy hardware implementation and can widely make use of the prior knowledge we have on MVL while constructing an MVL network [11,17]. Recently, GA [18] were also proposed to constitute an important avenue for solving such a problem.…”

A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks

“…Furthermore, although Genetic Algorithms provide an alternative method to problems that are different to solve with traditional optimization techniques, they suffer from poor convergence properties and difficulties to reach high-quality solutions in reasonable time [38]. In [39,40], the authors proposed a learning MVL network that uses the prior knowledge we have on MVL network while constructing an MVL network and conducts learning in a manner analogous to neural back-propagation. In these techniques, derivatives of the node functions are required, but they generally do not exist.…”