An evolutionary algorithm of feature accumulation for the construction of neural networks
Numerical methods and programming, Tome 2 (2001) no. 2, pp. 88-108.

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

A description of a new algorithm for the automatic neural network construction technique that involves positive features of the evolutionary and constructive approaches is presented. The main idea of the algorithm is based on the following: at each step, a neural network is increased by adding blocks of new neurons having a maximal influence on the error reduction. The search for the blocks is implemented with genetic algorithms. The process of constructing a neural network ends up when the network's error achieves a prescribed value. The efficiency of this algorithm is validated with the use of benchmark problems.
Keywords: neural networks, genetic algorithms, automation of network construction, network modeling.
@article{VMP_2001_2_2_a6,
     author = {V. V. Tiouterev},
     title = {An evolutionary algorithm of feature accumulation for the construction of neural networks},
     journal = {Numerical methods and programming},
     pages = {88--108},
     publisher = {mathdoc},
     volume = {2},
     number = {2},
     year = {2001},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VMP_2001_2_2_a6/}
}
TY  - JOUR
AU  - V. V. Tiouterev
TI  - An evolutionary algorithm of feature accumulation for the construction of neural networks
JO  - Numerical methods and programming
PY  - 2001
SP  - 88
EP  - 108
VL  - 2
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VMP_2001_2_2_a6/
LA  - ru
ID  - VMP_2001_2_2_a6
ER  - 
%0 Journal Article
%A V. V. Tiouterev
%T An evolutionary algorithm of feature accumulation for the construction of neural networks
%J Numerical methods and programming
%D 2001
%P 88-108
%V 2
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VMP_2001_2_2_a6/
%G ru
%F VMP_2001_2_2_a6
V. V. Tiouterev. An evolutionary algorithm of feature accumulation for the construction of neural networks. Numerical methods and programming, Tome 2 (2001) no. 2, pp. 88-108. http://geodesic.mathdoc.fr/item/VMP_2001_2_2_a6/