Facebook pixel tracking

The Science and Information (SAI) Organization publishes open-access peer-reviewed journals in computer science and artificial intelligence.

Contact Info
Email info@thesai.org
Website thesai.org
Follow Us
Contact Info
Email info@thesai.org
Follow Us
Research Article | Open Access |

Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks

Author 1: Marina Adriana Mercioni Author 2: Alexandru Tiron Author 3: Stefan Holban
International Journal of Advanced Computer Science and Applications (IJACSA) · Vol. 10, No. 4 · Published 2019 · Cited by 11

DOI: 10.14569/IJACSA.2019.0100406

Download PDF Cite Call for Papers

Abstract

The paper proposes the dynamic modification of the activation function in a learning technique, more exactly backpropagation algorithm. The modification consists in changing slope of sigmoid function for activation function according to increase or decrease the error in an epoch of learning. The study was done using the Waikato Environment for Knowledge Analysis (WEKA) platform to complete adding this feature in Multilayer Perceptron class. This study aims the dynamic modification of activation function has changed to relative gradient error, also neural networks with hidden layers have not used for it.

Keywords

Artificial neural networks activation function sigmoid function WEKA multilayer perceptron instance classifier gradient rate metric performance dynamic modification

How to Cite this Article

Mercioni, M. A., Tiron, A., & Holban, S. (2019). Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks. International Journal of Advanced Computer Science and Applications, 10(4). https://doi.org/10.14569/IJACSA.2019.0100406

Mercioni, Marina Adriana, et al.. "Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks." International Journal of Advanced Computer Science and Applications, vol. 10, no. 4, 2019, https://doi.org/10.14569/IJACSA.2019.0100406.

@article{Mercioni2019,
  title     = {Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {10},
  number    = {4},
  year      = {2019},
  publisher = {The Science and Information Organization},
  author    = {Marina Adriana Mercioni and Alexandru Tiron and Stefan Holban},
  doi       = {10.14569/IJACSA.2019.0100406},
  url       = {https://doi.org/10.14569/IJACSA.2019.0100406}
}

Open Access — licensed under a Creative Commons Attribution 4.0 International License. Unrestricted use, distribution, and reproduction in any medium, even commercially, as long as the original work is properly cited.

Back to Issue
IJACSA Journal Cover

Call for Papers - Important Dates

Volume 17 No. 11, November 2026
Paper Submission Due October 25, 2026
Review Notification November 15, 2026
Publication Date November 30, 2026
Call for Papers Submit Paper

IJACSA