Geodesic
About the maximum information and maximum likelihood principles
Kybernetika, Tome 34 (1998) no. 4, p. [485].

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

Neural networks with radial basis functions are considered, and the Shannon information in their output concerning input. The role of information- preserving input transformations is discussed when the network is specified by the maximum information principle and by the maximum likelihood principle. A transformation is found which simplifies the input structure in the sense that it minimizes the entropy in the class of all information-preserving transformations. Such transformation need not be unique - under some assumptions it may be any minimal sufficient statistics.
Classification : 62B10, 62M45, 68T05, 92B20
Keywords: neural networks; radial basis functions; entropy minimization 
@article{KYB_1998__34_4_a21,
     author = {Vajda, Igor and Grim, Ji\v{r}{\'\i}},
     title = {About the maximum information and maximum likelihood principles},
     journal = {Kybernetika},
     pages = {[485]},
     publisher = {mathdoc},
     volume = {34},
     number = {4},
     year = {1998},
     zbl = {1274.62644},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_1998__34_4_a21/}
}
TY  - JOUR
AU  - Vajda, Igor
AU  - Grim, Jiří
TI  - About the maximum information and maximum likelihood principles
JO  - Kybernetika
PY  - 1998
SP  - [485]
VL  - 34
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/KYB_1998__34_4_a21/
LA  - en
ID  - KYB_1998__34_4_a21
ER  - 
%0 Journal Article
%A Vajda, Igor
%A Grim, Jiří
%T About the maximum information and maximum likelihood principles
%J Kybernetika
%D 1998
%P [485]
%V 34
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/KYB_1998__34_4_a21/
%G en
%F KYB_1998__34_4_a21
Vajda, Igor; Grim, Jiří. About the maximum information and maximum likelihood principles. Kybernetika, Tome 34 (1998) no. 4, p. [485]. http://geodesic.mathdoc.fr/item/KYB_1998__34_4_a21/