Version 1
: Received: 5 April 2023 / Approved: 6 April 2023 / Online: 6 April 2023 (08:55:22 CEST)
How to cite:
Tümer Sivri, T.; Pervan Akman, N.; Berkol, A. The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models. Preprints2023, 2023040079. https://doi.org/10.20944/preprints202304.0079.v1
Tümer Sivri, T.; Pervan Akman, N.; Berkol, A. The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models. Preprints 2023, 2023040079. https://doi.org/10.20944/preprints202304.0079.v1
Tümer Sivri, T.; Pervan Akman, N.; Berkol, A. The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models. Preprints2023, 2023040079. https://doi.org/10.20944/preprints202304.0079.v1
APA Style
Tümer Sivri, T., Pervan Akman, N., & Berkol, A. (2023). The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models. Preprints. https://doi.org/10.20944/preprints202304.0079.v1
Chicago/Turabian Style
Tümer Sivri, T., Nergis Pervan Akman and Ali Berkol. 2023 "The Impact of Irrationals on the Range of Arctan Activation Function for Deep Learning Models" Preprints. https://doi.org/10.20944/preprints202304.0079.v1
Abstract
Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.
Keywords
Deep neural networks; Activation functions; Multi-class classification; Time-Series prediction; Reuters data; Energy trade value
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
