Geodesic
Training an artificial neural network
News of the Kabardin-Balkar scientific center of RAS, no. 6 (2023), pp. 95-102.

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

Particle swarm optimization (PSO) and Jaya are heuristic optimization algorithms that are used to find optimal solutions in optimization problems. Each of these methods has its own advantages and disadvantages, and the choice between them depends on the specific optimization problem and performance requirements. This paper proposes a hybrid of PSO and Jaya algorithms to improve optimization efficiency. In this paper PSO, Jaya, PSOJaya are used as artificial neural network (ANN) training methods for the classification task on the Balance Scale dataset. The results of the hybrid algorithm are compared with the results of the Backpropagation, PSO and Jaya algorithms. The test calculations compare the algorithms based on the mean, median, standard deviation, and "best" minimum error value after 30 simulations. The experiment results show that the ANN trained with PSOJaya has higher accuracy than the one trained with Backpropagation, PSO and Jaya.
Mots-clés : heuristic algorithm, ANN, classification
Keywords: optimization, particle swarm method (PSO), Jaya, Backpropagation, hybrid algorithm, pipeline hybridization 
@article{IZKAB_2023_6_a8,
     author = {E. M. Kazakova},
     title = {Training an artificial neural network},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {95--102},
     publisher = {mathdoc},
     number = {6},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a8/}
}
TY  - JOUR
AU  - E. M. Kazakova
TI  - Training an artificial neural network
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2023
SP  - 95
EP  - 102
IS  - 6
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a8/
LA  - ru
ID  - IZKAB_2023_6_a8
ER  - 
%0 Journal Article
%A E. M. Kazakova
%T Training an artificial neural network
%J News of the Kabardin-Balkar scientific center of RAS
%D 2023
%P 95-102
%N 6
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a8/
%G ru
%F IZKAB_2023_6_a8
E. M. Kazakova. Training an artificial neural network. News of the Kabardin-Balkar scientific center of RAS, no. 6 (2023), pp. 95-102. http://geodesic.mathdoc.fr/item/IZKAB_2023_6_a8/

[1] J. Kennedy, R. Eberhart, “Particle Swarm Optimization”, IEE International Conference on Neural Networks, 1995, 1942–1948 | DOI

[2] R. Rao, “Jaya: A simple and new optimization algorithm for solving constrained and unconstrained optimization problems”, Int J Indus Eng Comput, 1:7 (2016), 19–34 | DOI

[3] A. P. Karpenko, Sovremennye algoritmy poiskovoi optimizatsii. Algoritmy, vdokhnovlennye prirodoi, MGTU im. N. E. Baumana, 2 izdanie. M., 2017, 446 pp.

[4] H. Garg, “A hybrid PSO-GA algorithm for constrained optimization problems”, Applied Mathematics and Computation, 274 (2016), 292–305 | DOI | MR | Zbl

[5] S. Mirjalili, S. Z.M. Hashim, “A new hybrid PSOGSA algorithm for function optimization”, Proceedings of ICCIA 2010-2010 International Conference on Computer and Information Application, 2010, 374–377 | DOI

[6] F. A. Senel, F. Yuksel A. S. Gokce et al, “A novel hybrid PSO-GWO algorithm for optimization problems”, Engineering with Computers, 35 (2019), 1359–1373 | DOI

[7] Y. Zhou, P. A. Shengyu, “Hybrid Co-evolutionary particle swarm optimization algorithm for solving constrained engineering design problems”, J. Comput, 6:5 (2010), 965–972 | DOI | MR

[8] S. A. Mirjalili, S. Z.M. Hashim, H. M. Sardroudi, “Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm”, Applied Mathematics and Computation, 22:218 (2012), 11125–11137 | DOI | MR | Zbl

[9] F. E.F. Junior, G. G. Yen, “Particle swarm optimization of deep neural networks architectures for image classification”, Swarm and Evolutionary Computation, 49 (2019), 62–74 | DOI

[10] B. A. Garro, R. A. Vazquez, “Designing artificial neural networks using particle swarm optimization algorithms”, Computational intelligence and neuroscience, 2015, 61 | DOI

[11] J. R. Zhang, J. Zhang, T. M. Lok, M. R. Lyu, “A hybrid particle swarm optimization-backpropagation algorithm for feedforward neural network training”, Applied mathematics and computation, 2:185 (2007), 1026–1037 | DOI | MR

[12] R. Siegler, Balance Scale. UCI Machine Learning Repository, 1994 | DOI