Multi-Layer Perceptron Training by Genetic Algorithms


DOI: https://doi.org/10.15308/Sinteza-2020-301-306
Authors:
Luka Gajić
Dušan Cvetnić
Timea Bezdan
Miodrag Živković
Nebojša Bačanin Džakula

Download full paper

Keywords:
ANN, neural networks, training, genetic algorithm


Abstract:
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.

CITATION:

IEEE format

L. Gajić, D. Cvetnić, T. Bezdan, M. Živković, N. Bačanin Džakula, “Multi-Layer Perceptron Training by Genetic Algorithms,” in Sinteza 2020 - International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, 2020, pp. 301-306. doi:10.15308/Sinteza-2020-301-306

APA format

Gajić, L., Cvetnić, D., Bezdan, T., Živković, M., Bačanin Džakula, N. (2020). Multi-Layer Perceptron Training by Genetic Algorithms. Paper presented at Sinteza 2020 - International Scientific Conference on Information Technology and Data Related Research. doi:10.15308/Sinteza-2020-301-306

BibTeX format
Download

RefWorks Tagged format
Download