On a fuzzy-neural hierarchical controller with a self-generating knowledge base

Rajesh M. Kandadai, James M. Tien

Research output: Contribution to journalConference article


We present an innovative fuzzy-neural architecture that is able to automatically generate a knowledge base, in an extractable form, for use in hierarchical knowledge-based controllers. The knowledge base is in the form of a linguistic rule base appropriate for a fuzzy inference system. We modify Berenji and Khedkar's GARIC architecture [3] to a hierarchical controller and enable it to automatically generate a knowledge base. A pseudo-supervised learning scheme using reinforcement learning and error backpropagation is employed. Example applications are provided to underscore its viability.

Original languageEnglish (US)
Pages (from-to)2625-2630
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
StatePublished - Dec 1 1996
EventProceedings of the 1996 IEEE International Conference on Systems, Man and Cybernetics. Part 4 (of 4) - Beijing, China
Duration: Oct 14 1996Oct 17 1996


ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this