Adaptive–intelligent control by neural-net systems

✍ Scribed by Yoshitake Yamazaki; Geuntaek Kang; Moyuru Ochiai

• Publisher: John Wiley and Sons
• Year: 1998
• Tongue: English
• Weight: 215 KB
• Volume: 13
• Category: Article
• ISSN: 0884-8173
• DOI: 10.1002/(sici)1098-111x(199806)13:6<503::aid-int6>3.0.co;2-p

✦ Synopsis

Adaptive᎐intelligent control by neural-net systems is discussed. Actual adaptive᎐intelligent control is realized in a general system through the following two hierarchical steps: Ž . Ž 1 choosing a hierarchical coordinate system associated with the environment of the . Ž system and constructing the hierarchical evaluation functions specifying its control . Ž . states and 2 finding a set of the most appropriate hierarchical values for the control Ž . parameters giving the minimum value to the evaluation function .

Step 1 establishes Ž . ''intelligently self-controllable thinking algorithms'' with human-like intelligence for Ž . Ž . various events concepts .

Step 2 studies the intelligently self-controllable thinking algorithms for finding the most appropriate state. Adaptive᎐intelligent control by neural-Ž . net systems is realized by integrating both intelligently self-controllable thinking algorithms on the neural-net systems. Here step 2 is mainly discussed in the neural-net systems of Boltzmann type machines using the method of stochastic dynamics.