ALGORITHM FOR FINDING SIGNIFICANT FACTORS OF A COMPUTER MODEL USING DEEP LEARNING METHODS

Authors

  • Nataliia ORIEKHOVA V. M. Glushkov Institute of Cybernetics of the National Academy of Sciences Author
  • Oleksandr LUKYANOV V. M. Glushkov Institute of Cybernetics of the National Academy of Sciences of Ukraine Author

DOI:

https://doi.org/10.17721/3041-2323.2024.242-247

Keywords:

modeling, feature selection, neural network, dense level, activation function, number of epochs, data sample, training, prediction, attribute significance

Abstract

The article proposes an algorithm based on a small neural network for feature selection for data sets in which the number of training samples slightly exceeds the number of attributes.

References

Bigdan, V. B., Pepelyaev, V. A., & Chornyi, Y. M. (2006). Unified scheme for optimization–simulation experiments. Problems of Programming, 2-3, 728–733 [in Ukrainian].

Chollet, F. (2021). Deep learning with Python. Simon and Schuster.

Keras. (n. d.). About Keras. Retrieved May 6, 2025, from https://keras.io/about/

Title

Downloads

Published

01.10.2024

Issue

Vol. 1 No. 1 (2024): APPLIED INFORMATION SYSTEMS AND TECHNOLOGIES IN THE DIGITAL SOCIETY

Section

Статті

License

Copyright (c) 2024 Applied information systems and technologies in the digital society

Creative Commons License

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