Geodesic
On some properties of randomized machine learning procedures in the presence of noisy data
Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2023), pp. 89-95.

Voir la notice de l'article provenant de la source Math-Net.Ru

We study various models of measuring noises in the procedures of randomized entropy estimation of probability density functions: additive and multiplicative, measuring noises at the input and output of the object’s model. The properties of entropy-optimal probability density functions are studied, it is shown that the measurement noises corresponding to them are heteroscedastic.
Keywords: entropy estimation, density functions, heteroscedastic noise, variation models.
Mots-clés : Lagrange multipliers 
@article{ITVS_2023_2_a8,
     author = {Yu. S. Popkov},
     title = {On some properties of randomized machine learning procedures in the presence of noisy data},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {89--95},
     publisher = {mathdoc},
     number = {2},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2023_2_a8/}
}
TY  - JOUR
AU  - Yu. S. Popkov
TI  - On some properties of randomized machine learning procedures in the presence of noisy data
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2023
SP  - 89
EP  - 95
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2023_2_a8/
LA  - ru
ID  - ITVS_2023_2_a8
ER  - 
%0 Journal Article
%A Yu. S. Popkov
%T On some properties of randomized machine learning procedures in the presence of noisy data
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2023
%P 89-95
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2023_2_a8/
%G ru
%F ITVS_2023_2_a8
Yu. S. Popkov. On some properties of randomized machine learning procedures in the presence of noisy data. Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2023), pp. 89-95. http://geodesic.mathdoc.fr/item/ITVS_2023_2_a8/