Geodesic
Learning extremal regulator implementation by a stochastic automaton and stochastic approximation theory
Applications of Mathematics, Tome 25 (1980) no. 5, pp. 315-323.

Voir la notice de l'article provenant de la source Czech Digital Mathematics Library

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},
     publisher = {mathdoc},
     volume = {25},
     number = {5},
     year = {1980},
     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
PB  - mathdoc
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
%I mathdoc
%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. http://geodesic.mathdoc.fr/articles/10.21136/AM.1980.103867/

Cité par Sources :