Elastic Fuzzy Logic: A Better Fit to Neurocontrol and True Intelligence

Abstract

Since 1990 or so (Werbos, 1992), there has been great interest in using adaptive methods taken from neural network theory to adapt fuzzy-logic networks or other fuzzy systems. The basic idea is to use fuzzy logic as a kind of translation technology, to go back and forth between the words of a human expert and the equations of a controller, classifier, or other useful system. One can then use neural network methods to adapt that system to improve performance. Designs of this sort already have proved useful. However, the existing designs do not live up to the full potential of this approach, and they do not achieve anything like brainstyle “intelligence.” This article will propose a two-fold approach to achieving the full potential of such hybrid systems: (1) the use of elastic fuzzy logic (ELF), a new extension of fuzzy logic that makes it possible to combine the best of fuzzy logic and neural networks; and (2) the use of advanced learning techniques-using some ELF components-that make it possible to perform true planning or optimization over time on an adaptive basis (White and Sofge, 1992). Pseudocode examples will be given to help in application. The article will also discuss symbolic reasoning, and links to the Real-time Control System (RCS) of Albus (1990), which represents the state of the art in classical AI for control.