DocumentCode
300547
Title
Stability analysis of open-loop learning in CMAC neural networks
Author
Campagna, David ; Kraft, Gordon
Author_Institution
Dept. of Electr. & Comput. Eng., New Hampshire Univ., Durham, NH, USA
Volume
1
fYear
1995
fDate
21-23 Jun 1995
Firstpage
852
Abstract
This paper presents the results of a CMAC neural network stability analysis in which it is postulated that the function being learned by the CMAC is itself adequately represented by a fully trained CMAC of identical form. It is shown, using Lyapunov techniques, that the CMAC weights being trained converge to the corresponding target weights. Results are presented for single-input single-output, multiple-input single-output, and multiple-input multiple output systems
Keywords
Lyapunov methods; learning (artificial intelligence); multivariable control systems; neurocontrollers; stability; CMAC neural networks; Lyapunov techniques; MIMO systems; MISO systems; SISO systems; convergence; neural control; open-loop learning; stability analysis; Computer networks; Convergence; Equations; Input variables; Intelligent networks; Lyapunov method; Neural networks; Open loop systems; Stability analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
American Control Conference, Proceedings of the 1995
Conference_Location
Seattle, WA
Print_ISBN
0-7803-2445-5
Type
conf
DOI
10.1109/ACC.1995.529369
Filename
529369
Link To Document