Pregled bibliografske jedinice broj: 49623
A Knowledge-Base Generating Fuzzy-Neural Controller
A Knowledge-Base Generating Fuzzy-Neural Controller // Preprints of the IFAC Symposium on Artificial Intelligence in Real Time Control, AIRTC-2000 / Rudas, Imre J. ; Tar, Jozsef K. (ur.).
Budimpešta: International Federation of Automatic Control, 2000. str. 211-216 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 49623 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A Knowledge-Base Generating Fuzzy-Neural Controller
Autori
Petrović, Ivan ; Maček, Kristijan ; Perić, Nedjeljko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Preprints of the IFAC Symposium on Artificial Intelligence in Real Time Control, AIRTC-2000
/ Rudas, Imre J. ; Tar, Jozsef K. - Budimpešta : International Federation of Automatic Control, 2000, 211-216
Skup
IFAC Symposium on Artificial Intelligence in Real Time Control, AIRTC-2000
Mjesto i datum
Budimpešta, Mađarska, 02.10.2000. - 04.10.2000
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
ekspertni sustavi; inteligentno upravljanje; neizrazita logika; neuronske mreže
(expert systems; intelligent control; fuzzy logic; neural networks)
Sažetak
This paper presents a modification to the Kandadai and Tien's learning algorithm for tuning a fuzzy-neural controller that is able to automatically generate a knowledge base. Tuning is based on reinforcements from a dynamical system, thus giving a pseudosupervised learning scheme using error backpropagation. Originally, a weak reinforcement in the form of a binary failure signal was assumed which proved to be insufficient in terms of steady-state error. Therefore, a continuous reinforcement signal is applied enabling the system to correct the error as well as decreasing the overall control effort in the learning phase.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
