Multi-Layer Perceptron Training by Genetic Algorithms

Izdanje: International Scientific Conference on Information Technology and Data Related Research

DOI: 10.15308/Sinteza-2020-301-306

Oblast: Advanced Computing

Stranice: 301-306

Apstrakt:
In this paper, the authors are presenting one of the ways to train Artificial Neural Networks (ANN) using a predefined set of weights as biases as input parameters, generated by the Genetic Algorithm (GA). This approach solves the problem of hyperparameter tuning for ANN, which is an NP-hard space search problem and will be further explained in the paper. The genetic algorithm generates a population of potential solutions in each iteration and then after a series of solutions variables modification (crossover, mutation, etc.) ranks them based on their fitness values. The algorithm itself is tested on a standard Multi-layer Perceptron (MLP) artificial neural network and results are similar compared to other techniques of training.
Ključne reči: ANN, neural networks, training, genetic algorithm
Priložene datoteke:
  • 301-306 ( veličina: 425,35 KB, broj pregleda: 395 )

Preuzimanje citata:

BibTeX format
@article{article,
  author  = {L. Gajić, D. Cvetnić, T. Bezdan, M. Živković and N. Bačanin Džakula}, 
  title   = {Multi-Layer Perceptron Training by Genetic Algorithms},
  journal = {International Scientific Conference on Information Technology and Data Related Research},
  year    = 2020,
  pages   = {301-306},
  doi     = {10.15308/Sinteza-2020-301-306}
}
RefWorks Tagged format
RT Conference Proceedings
A1 Luka Gajić
A1 Dušan Cvetnić
A1 Timea Bezdan
A1 Miodrag Živković
A1 Nebojša Bačanin Džakula
T1 Multi-Layer Perceptron Training by Genetic Algorithms
AD Univerzitet Singidunum, Beograd, Beograd, Srbija
YR 2020
NO doi: 10.15308/Sinteza-2020-301-306
Unapred formatirani prikaz citata
L. Gajić, D. Cvetnić, T. Bezdan, M. Živković and N. Bačanin Džakula, Multi-Layer Perceptron Training by Genetic Algorithms, Univerzitet Singidunum, Beograd, 2020, doi:10.15308/Sinteza-2020-301-306