ADAPTIVE-INTELLIGENT CONTROL BY NEURAL-NET SYSTEMS

Adaptive-intelligent control by neural-net systems is discussed. Actua l adaptive-intelligent control is realized in a general system through the following two hierarchical steps: (1) choosing a hierarchical coo rdinate system (associated with the environment of the system) and con structing the hierarchical evaluation functions (specifying its contro l states) and (2) finding a set of the mast appropriate hierarchical v alues for the control parameters (giving the minimum value to the eval uation function). Step 1 establishes ''intelligently self-controllable (thinking) algorithms'' with human-like intelligence for various even ts (concepts). Step 2 studies the intelligently self-controllable (thi nking) algorithms for finding the most appropriate state. Adaptive-int elligent control by neural-net systems is realized by integrating both intelligently self-controllable (thinking) algorithms on the neural-n et systems. Here step 2 is mainly discussed in the neural-net systems of Boltzmann type machines using the method of stochastic dynamics. (C ) 1998 John Wiley & Sons, Inc.