Influence of the Neural Network Hyperparameters on its Numerical Conditioning

S. V. Sholtanyuk ()

Digital Transformation, 2020, issue 1

Abstract: In this paper, the task of assessment of numerical conditioning of multilayer perceptron, forecasting time series with sliding window method, has been considered. Performance of the forecasting perceptron with various hyperparameters sets, with different amount of neurons and various activation functions in particular, has been considered. Main factors, influencing on the neural net conditioning, have been revealed, as well as performance features, when using various activation functions. Formulas for assessment of condition numbers of individual components of the forecasting perceptron and of the neural network itself have been proposed. Comparative analysis of results of training the forecasting perceptron with various hyperparameters on modeled time series has been performed. Conditions, providing the best stability and conditioning for the neural network, have been formulated.

Date: 2020
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://dt.bsuir.by/jour/article/viewFile/478/181 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abx:journl:y:2020:id:478

Access Statistics for this article

More articles in Digital Transformation from Educational Establishment “Belarusian State University of Informatics and Radioelectronicsâ€
Bibliographic data for series maintained by Ð ÐµÐ´Ð°ÐºÑ†Ð¸Ñ ().