Geodesic
Stability of two-layer recursive neural networks
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 5 (2013) no. 2, pp. 151-154

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

The stability conditions are described for the discrete neural networks. Stability regions are constructed in the parameter space for these networks. The problem reduces to the stability problem for the matrix difference equations of higher order with delay. The main tool is the stability cone.
Keywords: neural networks; difference matrix equations; stability of difference equations; two-layer network. 
@article{VYURM_2013_5_2_a22,
     author = {S. A. Ivanov},
     title = {Stability of two-layer recursive neural networks},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a, Matematika, mehanika, fizika},
     pages = {151--154},
     publisher = {mathdoc},
     volume = {5},
     number = {2},
     year = {2013},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VYURM_2013_5_2_a22/}
}
TY  - JOUR
AU  - S. A. Ivanov
TI  - Stability of two-layer recursive neural networks
JO  - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
PY  - 2013
SP  - 151
EP  - 154
VL  - 5
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VYURM_2013_5_2_a22/
LA  - ru
ID  - VYURM_2013_5_2_a22
ER  - 
%0 Journal Article
%A S. A. Ivanov
%T Stability of two-layer recursive neural networks
%J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
%D 2013
%P 151-154
%V 5
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VYURM_2013_5_2_a22/
%G ru
%F VYURM_2013_5_2_a22
S. A. Ivanov. Stability of two-layer recursive neural networks. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 5 (2013) no. 2, pp. 151-154. http://geodesic.mathdoc.fr/item/VYURM_2013_5_2_a22/