|
Avtomatika i Telemekhanika, 1989, Issue 2, Pages 158–184
(Mi at6212)
|
|
|
|
Simulation of Behavior and Intelligence
Convergence properties of associative memory storage for learning control systems
J. Militzera, P. C. Parksb a Darmstadt, FRG
b Swindon, England
Abstract:
The associative memory system for learning control systems developed by J. S. Albus is described, and the underlying mathematical algorithm is interpreted as a process of dropping perpendiculars to a series of hyperplanes. The convergence of this process is investigated for what is called «cyclic training» in some detail. Here the algorithm either converges to a fixed point or tends to a «limit cycle». «Random training» is also possible in practice, and, in certain circumstances, the algorithm will also converge to a fixed point. In general, however, it is possible at the present time only to make certain conjectures about the convergence of the random training process to so-called «capture zones». Illustrations of the various concepts developed in the paper are given in Appendices.
Received: 17.03.1988
Citation:
J. Militzer, P. C. Parks, “Convergence properties of associative memory storage for learning control systems”, Avtomat. i Telemekh., 1989, no. 2, 158–184; Autom. Remote Control, 50:2 (1989), 254–286
Linking options:
https://www.mathnet.ru/eng/at6212 https://www.mathnet.ru/eng/at/y1989/i2/p158
|
Statistics & downloads: |
Abstract page: | 122 | Full-text PDF : | 56 | First page: | 2 |
|