Previous |  Up |  Next


Title: Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory (English)
Author: Brůha, Ivan
Language: English
Journal: Aplikace matematiky
ISSN: 0373-6725
Volume: 25
Issue: 5
Year: 1980
Pages: 315-323
Summary lang: English
Summary lang: Czech
Summary lang: Russian
Category: math
Summary: There exist many different approaches to the investigation of the characteristics of learning system. These approaches use different branches of mathematics and, thus, obtain different results, some of them are too complicated and others do not match the results of practical experiments. This paper presents the modelling of learning systems by means of stochastic automate, mainly one particular model of a learning extremal regulator. The proof of convergence is based on Dvoretzky's Theorem on stochastic approximations. Experiments have proved the theory of stochastic automata and stochastic approximations to be quite suitable means for studying the learning systems. (English)
Keyword: learning systems
Keyword: stochastic automata
Keyword: convergence of the learning algorithm
MSC: 62L20
MSC: 68D25
MSC: 68Q45
MSC: 68T05
MSC: 68W99
MSC: 92A90
MSC: 93E03
idZBL: Zbl 0495.68080
idMR: MR0590486
DOI: 10.21136/AM.1980.103867
Date available: 2008-05-20T18:14:55Z
Last updated: 2020-07-28
Stable URL:
Reference: [1] A. Paz: Introduction to probabilistic automata.Academic Press, New York and London 1971. Zbl 0234.94055, MR 0289222
Reference: [2] M. Л. Цетлин: О поведении конечных автоматов в случайных средах.Автоматика и телемеханика 22 (1961), 1345 - 1354. Zbl 1160.68305, MR 0141569
Reference: [3] В. И. Варшавский И. П. Воронцова: О поведении стохастических автоматов с переменной структурой.Автоматика и телемеханика 24 (1963), 353 - 360. Zbl 1214.14039, MR 0163810
Reference: [4] K. S. Fu T. J. Li: Formulation of learning automata and automata games.Information Sciences 1 (1969), 237-256. MR 0243950, 10.1016/S0020-0255(69)80010-1
Reference: [5] A. Dvoretzky: On stochastic approximation.Proc. 3rd Berkeley Symp. Math. Statist, and Probability, vol. 1, 39-55, Univ. of California Press, Berkeley, Cal., 1956. Zbl 0072.34701, MR 0084911
Reference: [6] I. Brůha: Comparing the theory of deterministic and probabilistic automata for modelling adaptive learning systems.(Czech). Ph. D. thesis, FEL ČVUT, 1973.
Reference: [7] P. Benedikt: Modelling learning systems by means of probabilistic automata.(Czech). Master Thesis, FEL ČVUT, 1974.
Reference: [8] K. S. Fu: Stochastic automata as models of learning systems.Proc. Symp. Сор. Information Sci., Columbus, Ohio, 1966.
Reference: [9] K. S. Fu Z. J. Nikolic: On some reinforcement techniques and their relation to the stochastic approximation.IEEE Trans. AC-11 (1966), 756-758. MR 0211798
Reference: [10] K. S. Narendra M. A. L. Thathachar: Learnig automata - a survey.IEEE Trans. SMC-4 (1974), 323-334. MR 0469583
Reference: [11] Y. Sawaragi N. Baba: Two $\epsilon$-optimal nonlinear reinforcement schemes for stochastic automata.IEEE Trans. SMC-4 (1974), 126-131. MR 0449946
Reference: [12] R. Viswanathan K. S. Narendra: Games of stochastic automata.IEEE Trans. SMC-4 (1974), 131-135.
Reference: [13] Z. Kotek I. Brůha V. Chalupa J. Jelínek: Adaptive and learning systems.(Czech). SNTL Praha, 1980.


Files Size Format View
AplMat_25-1980-5_2.pdf 1.263Mb application/pdf View/Open
Back to standard record
Partner of
EuDML logo