A knowledge-base generating hierarchical fuzzy-neural controller

Rajesh M. Kandadai, James M. Tien

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

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. First, we modify Berenji and Khedkar's GARIC architecture [4] to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.

Original languageEnglish
Pages (from-to)1531-1541
Number of pages11
JournalIEEE Transactions on Neural Networks
Volume8
Issue number6
DOIs
StatePublished - Dec 1 1997
Externally publishedYes

Fingerprint

Knowledge Base
Controller
Controllers
Reinforcement learning
Fuzzy inference
Backpropagation
Linguistics
Fuzzy Inference System
Rule Base
Back Propagation
Knowledge-based
Reinforcement Learning
Viability
Architecture
Form

Keywords

  • Expert system
  • Fuzzy inference
  • Fuzzy logic
  • Hierarchical controller
  • Neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

A knowledge-base generating hierarchical fuzzy-neural controller. / Kandadai, Rajesh M.; Tien, James M.

In: IEEE Transactions on Neural Networks, Vol. 8, No. 6, 01.12.1997, p. 1531-1541.

Research output: Contribution to journalArticle

@article{cfa8a518d19445e3abb486e941981b93,
title = "A knowledge-base generating hierarchical fuzzy-neural controller",
abstract = "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. First, we modify Berenji and Khedkar's GARIC architecture [4] to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.",
keywords = "Expert system, Fuzzy inference, Fuzzy logic, Hierarchical controller, Neural networks",
author = "Kandadai, {Rajesh M.} and Tien, {James M.}",
year = "1997",
month = "12",
day = "1",
doi = "10.1109/72.641474",
language = "English",
volume = "8",
pages = "1531--1541",
journal = "IEEE Transactions on Neural Networks",
issn = "1045-9227",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - A knowledge-base generating hierarchical fuzzy-neural controller

AU - Kandadai, Rajesh M.

AU - Tien, James M.

PY - 1997/12/1

Y1 - 1997/12/1

N2 - 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. First, we modify Berenji and Khedkar's GARIC architecture [4] to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.

AB - 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. First, we modify Berenji and Khedkar's GARIC architecture [4] to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.

KW - Expert system

KW - Fuzzy inference

KW - Fuzzy logic

KW - Hierarchical controller

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=0031276493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031276493&partnerID=8YFLogxK

U2 - 10.1109/72.641474

DO - 10.1109/72.641474

M3 - Article

VL - 8

SP - 1531

EP - 1541

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

SN - 1045-9227

IS - 6

ER -