Geodesic
Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory
Applications of Mathematics, Tome 25 (1980) no. 5, pp. 315-323
Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

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.
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.
DOI : 10.21136/AM.1980.103867
Classification : 62L20, 68D25, 68Q45, 68T05, 68W99, 92A90, 93E03
Keywords: learning systems; stochastic automata; convergence of the learning algorithm 
@article{10_21136_AM_1980_103867,
     author = {Br\r{u}ha, Ivan},
     title = {Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory},
     journal = {Applications of Mathematics},
     pages = {315--323},
     year = {1980},
     volume = {25},
     number = {5},
     doi = {10.21136/AM.1980.103867},
     mrnumber = {0590486},
     zbl = {0495.68080},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.21136/AM.1980.103867/}
}
TY  - JOUR
AU  - Brůha, Ivan
TI  - Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory
JO  - Applications of Mathematics
PY  - 1980
SP  - 315
EP  - 323
VL  - 25
IS  - 5
UR  - http://geodesic.mathdoc.fr/articles/10.21136/AM.1980.103867/
DO  - 10.21136/AM.1980.103867
LA  - en
ID  - 10_21136_AM_1980_103867
ER  - 
%0 Journal Article
%A Brůha, Ivan
%T Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory
%J Applications of Mathematics
%D 1980
%P 315-323
%V 25
%N 5
%U http://geodesic.mathdoc.fr/articles/10.21136/AM.1980.103867/
%R 10.21136/AM.1980.103867
%G en
%F 10_21136_AM_1980_103867
Brůha, Ivan. Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory. Applications of Mathematics, Tome 25 (1980) no. 5, pp. 315-323. doi: 10.21136/AM.1980.103867

[1] A. Paz: Introduction to probabilistic automata. Academic Press, New York and London 1971. | MR | Zbl

[2] M. Л. Цетлин: О поведении конечных автоматов в случайных средах. Автоматика и телемеханика 22 (1961), 1345 - 1354. | MR | Zbl

[3] В. И. Варшавский И. П. Воронцова: О поведении стохастических автоматов с переменной структурой. Автоматика и телемеханика 24 (1963), 353 - 360. | MR | Zbl

[4] K. S. Fu T. J. Li: Formulation of learning automata and automata games. Information Sciences 1 (1969), 237-256. | DOI | MR

[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. | MR | Zbl

[6] I. Brůha: Comparing the theory of deterministic and probabilistic automata for modelling adaptive learning systems. (Czech). Ph. D. thesis, FEL ČVUT, 1973.

[7] P. Benedikt: Modelling learning systems by means of probabilistic automata. (Czech). Master Thesis, FEL ČVUT, 1974.

[8] K. S. Fu: Stochastic automata as models of learning systems. Proc. Symp. Сор. Information Sci., Columbus, Ohio, 1966.

[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

[10] K. S. Narendra M. A. L. Thathachar: Learnig automata - a survey. IEEE Trans. SMC-4 (1974), 323-334. | MR

[11] Y. Sawaragi N. Baba: Two $\epsilon$-optimal nonlinear reinforcement schemes for stochastic automata. IEEE Trans. SMC-4 (1974), 126-131. | MR

[12] R. Viswanathan K. S. Narendra: Games of stochastic automata. IEEE Trans. SMC-4 (1974), 131-135.

[13] Z. Kotek I. Brůha V. Chalupa J. Jelínek: Adaptive and learning systems. (Czech). SNTL Praha, 1980.

Cité par Sources :