Industry 4.0
Vol. 6 (2021), Issue 4, pg(s) 135-138

TECHNOLOGICAL BASIS OF “INDUSTRY 4.0”

Influence of the transfer function of the data classification process in a two – layer neural network

  • 1 Academy of Professional Studies Southern Serbia, Leskovac, Serbia
  • 2 University of Library Studies and Information Technologies, Sofia, Bulgaria

Abstract

This paper analyses the influence of transfer function choice and learning rate on a multilayer neural network in the classi fication process. The neural network is implemented in the Java programming language.

Keywords

References

  1. Duch, W., Jankowski N, (2001). Transfer functions: hidden possibilities for better neural networks. 9th European Symposium on Artificial Neural Networks, Bruges, Belgium.
  2. Maca P., Pech P., Pavlasek J., (2014) Comparing the selected transfer functions and local optimization methods for neural network flood runoff forecast. Mathematical Problems in Engineering. https://doi.org/10.1155/2014/782351
  3. Yonaba, H., F. Anctil, and V. Fortin. (2010). Comparing sigmoid transfer functions for neural network multistep ahead streamflow forecasting. Journal of Hydrologic Engineering 15(4). DOI: 10.1061/(ASCE)HE.1943-5584.0000188
  4. Rumelhart, D. et. al. (1996). Backpropagation: The basic theory. In P. Smolensky, M. C. Mozer, and D. E. Rumelhart(eds.) Mathematical Perspectives on Neural Networks. Erlbaum: NJ, 533- 566.
  5. Garvanova, M., Ivanov, V. (2020). Quality assessment of defocused image recovery algorithms. 3rd International Conference on Sensors, Signal and Image Processing, Prague, Czech Republic, doi: https://doi.org/10.1145/3441233.3441242.

Article full text

Download PDF