Geodesic
On the gradient of neuronetwork function
Vestnik rossijskih universitetov. Matematika, Tome 22 (2017) no. 3, pp. 552-557 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

The paper proposes a matrix formula for the gradient of neuronetwork function $\nabla_W f(X;W)$ with respect to the parameter vector $W$.
Keywords: neuronetwork function, neural network, backpropagation algorithm
Mots-clés : Hadamard product. 
@article{VTAMU_2017_22_3_a6,
     author = {N. M. Mishachev and A. M. Shmyrin},
     title = {On the gradient of neuronetwork function},
     journal = {Vestnik rossijskih universitetov. Matematika},
     pages = {552--557},
     year = {2017},
     volume = {22},
     number = {3},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VTAMU_2017_22_3_a6/}
}
TY  - JOUR
AU  - N. M. Mishachev
AU  - A. M. Shmyrin
TI  - On the gradient of neuronetwork function
JO  - Vestnik rossijskih universitetov. Matematika
PY  - 2017
SP  - 552
EP  - 557
VL  - 22
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/VTAMU_2017_22_3_a6/
LA  - ru
ID  - VTAMU_2017_22_3_a6
ER  - 
%0 Journal Article
%A N. M. Mishachev
%A A. M. Shmyrin
%T On the gradient of neuronetwork function
%J Vestnik rossijskih universitetov. Matematika
%D 2017
%P 552-557
%V 22
%N 3
%U http://geodesic.mathdoc.fr/item/VTAMU_2017_22_3_a6/
%G ru
%F VTAMU_2017_22_3_a6
N. M. Mishachev; A. M. Shmyrin. On the gradient of neuronetwork function. Vestnik rossijskih universitetov. Matematika, Tome 22 (2017) no. 3, pp. 552-557. http://geodesic.mathdoc.fr/item/VTAMU_2017_22_3_a6/

[1] C. Haykin, Neural Networks: A Comprehensive Foundation, Viliams, Moscow, 2006 (In Russian)

[2] D. E. Rumelhart, G. E. Hinton, R. J. Williams, “Learning Internal Representations by Error Propagation”, chapter 8, Parallel Distributed Processing, MIT Press, Cambridge, Massachusetts, 1986, 318–362