Geodesic
Training artificial neural networks with dynamic particle swarm optimisation
Matematičeskoe modelirovanie, Tome 24 (2012) no. 12, pp. 107-112.

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

Particle swarm optimisation has been successfully applied to train artificial feedforward neural networks before, however, considered problems were assumed to be static. Such assumption does not hold for many real-world problems. This article investigates the applicability of dynamic particle swarm optimisation algorithms as neural network training algorithms for dynamic classification problems. The performance of dynamic particle swarm optimization is compared to back-propagation, and dynamic particle swarm optimisation is shown to be a viable training algorithm for dynamic classification problems.
Keywords: artificial neural networks, supervised training, dynamic environments.
Mots-clés : particle swarm optimisation 
@article{MM_2012_24_12_a17,
     author = {A. S. Rakitianskaia and A. P. Engelbrecht},
     title = {Training artificial neural networks with dynamic particle swarm optimisation},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {107--112},
     publisher = {mathdoc},
     volume = {24},
     number = {12},
     year = {2012},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2012_24_12_a17/}
}
TY  - JOUR
AU  - A. S. Rakitianskaia
AU  - A. P. Engelbrecht
TI  - Training artificial neural networks with dynamic particle swarm optimisation
JO  - Matematičeskoe modelirovanie
PY  - 2012
SP  - 107
EP  - 112
VL  - 24
IS  - 12
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2012_24_12_a17/
LA  - ru
ID  - MM_2012_24_12_a17
ER  - 
%0 Journal Article
%A A. S. Rakitianskaia
%A A. P. Engelbrecht
%T Training artificial neural networks with dynamic particle swarm optimisation
%J Matematičeskoe modelirovanie
%D 2012
%P 107-112
%V 24
%N 12
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2012_24_12_a17/
%G ru
%F MM_2012_24_12_a17
A. S. Rakitianskaia; A. P. Engelbrecht. Training artificial neural networks with dynamic particle swarm optimisation. Matematičeskoe modelirovanie, Tome 24 (2012) no. 12, pp. 107-112. http://geodesic.mathdoc.fr/item/MM_2012_24_12_a17/

[1] Kennedy J., Eberhart R. C., “Particle swarm optimization”, Proceedings of the IEEE International Conference on Neural Networks, IV, Piscataway, USA, 1995, 1942–1948 | DOI

[2] Gudise V. G., Venayagamoorthy G. K., “Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks”, Proceedings of the IEEE Swarm Intelligence Symposium, Piscataway, USA, 110–117

[3] Duhain J. G. O. L., Particle swarm optimisation in dynamically changing environments — an empirical study, Master's thesis, University of Pretoria, Pretoria, South Africa, 2011

[4] Werbos P. J., Beyond Regression: New Tools for Prediction and Analysis in the Behavioural Sciences, PhD thesis, Harvard University, Boston, USA, 1974 | MR

[5] Rakitianskaia A., Engelbrecht A. P., “Training neural networks with PSO in dynamic environments”, Proceedings of the IEEE Congress on Evolutionary Computation, Piscataway, USA, 2009, 667–673 | DOI

[6] Harries M., “Splice-2 comparative evaluation: Electricity pricing”, Technical Report UNSW-CSE-TR-9905, Artificial Intelligence Group, School of Computer Science and Engineering, The University of New South Wales, Sydney 2052, Australia, July 1999