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. 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 language | English (US) |
|---|---|
| Title of host publication | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
| Editors | Anon |
| Publisher | IEEE |
| Pages | 2625-2630 |
| Number of pages | 6 |
| Volume | 4 |
| State | Published - 1996 |
| Externally published | Yes |
| Event | Proceedings of the 1996 IEEE International Conference on Systems, Man and Cybernetics. Part 4 (of 4) - Beijing, China Duration: Oct 14 1996 → Oct 17 1996 |
Other
| Other | Proceedings of the 1996 IEEE International Conference on Systems, Man and Cybernetics. Part 4 (of 4) |
|---|---|
| City | Beijing, China |
| Period | 10/14/96 → 10/17/96 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Control and Systems Engineering
Cite this
On a fuzzy-neural hierarchical controller with a self-generating knowledge base. / Kandadai, Rajesh M.; Tien, James M.
Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. ed. / Anon. Vol. 4 IEEE, 1996. p. 2625-2630.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - On a fuzzy-neural hierarchical controller with a self-generating knowledge base
AU - Kandadai, Rajesh M.
AU - Tien, James M.
PY - 1996
Y1 - 1996
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. 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.
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. 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.
UR - http://www.scopus.com/inward/record.url?scp=0030418058&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030418058&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0030418058
VL - 4
SP - 2625
EP - 2630
BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
A2 - Anon, null
PB - IEEE
ER -