NEUROEVOLUTION METHODS FOR FEEDFORWARD NEURAL NETWORKS

Authors

  • Юлия Ивановна Давидюк УО «Брестский государственный технический университет»

DOI:

https://doi.org/10.36773/1818-1212-2021-125-2-49-53

Keywords:

neural network, genetic algorithm, evolutionary programming, neuroevolution

Abstract

Various optimization methods and parameters of feedforward neural networks by evolutionary algorithms are considered.

The analysis of neuroevolutionary methods, basic properties and applicability of various variants of evolutionary optimization with direct coding of chromosomes for various architectures of feedforward neural networks are presented.

Operators of the genetic algorithm, advantages, disadvantages and features of their application are described for each method of neuroevolution. The comparison results are presented in tabular form.

 

 

 

Author Biography

Юлия Ивановна Давидюк, УО «Брестский государственный технический университет»

 

 

 

 

Downloads

Published

2021-06-29

How to Cite

(1)
Давидюк, Ю. И. NEUROEVOLUTION METHODS FOR FEEDFORWARD NEURAL NETWORKS. Вестник БрГТУ 2021, 49-53.

Issue

No. 2(125) (2021): Vestnik of Brest State Technical University

Section

Mechanical Engineering

License

Copyright (c) 2021 Brest State Technical University

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The work is provided under the terms of Creative Commons public license Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This license allows an unlimited number of persons to reproduce and share the Licensed Material in all media and formats. Any use of the Licensed Material shall contain an identification of its Creator(s) and must be for non-commercial purposes only. Users may not prevent other individuals from taking any actions allowed by the license.