Geodesic
Stability of multilayer recursive neural networks
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 7 (2015) no. 3, pp. 5-9

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

Numerical stability criteria are described for multilayer discrete-time neural networks. Stability domains in the space of parameters are built. The problem reduces to the stability problem for difference matrix equations of a higher order with delay. Stability cones are major tolls for problem solution.
Keywords: neural networks; difference matrix equations; stability of difference equations; multilayer network. 
@article{VYURM_2015_7_3_a0,
     author = {S. A. Ivanov and I. I. Blees},
     title = {Stability of multilayer recursive neural networks},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a, Matematika, mehanika, fizika},
     pages = {5--9},
     publisher = {mathdoc},
     volume = {7},
     number = {3},
     year = {2015},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VYURM_2015_7_3_a0/}
}
TY  - JOUR
AU  - S. A. Ivanov
AU  - I. I. Blees
TI  - Stability of multilayer recursive neural networks
JO  - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
PY  - 2015
SP  - 5
EP  - 9
VL  - 7
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VYURM_2015_7_3_a0/
LA  - ru
ID  - VYURM_2015_7_3_a0
ER  - 
%0 Journal Article
%A S. A. Ivanov
%A I. I. Blees
%T Stability of multilayer recursive neural networks
%J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
%D 2015
%P 5-9
%V 7
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VYURM_2015_7_3_a0/
%G ru
%F VYURM_2015_7_3_a0
S. A. Ivanov; I. I. Blees. Stability of multilayer recursive neural networks. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 7 (2015) no. 3, pp. 5-9. http://geodesic.mathdoc.fr/item/VYURM_2015_7_3_a0/