Fractional calculus applications in deep learning architectures
Journal of Interdisciplinary Mathematics · 2026 · 29 (3) · 693-700
DOI: 10.47974/jim-2504 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Interdisciplinary Mathematics, 2026. Verfasst von Chandrakant Deelip Kokane und 5 weiteren Autor:innen.
Abstract (Originalsprache)
The study investigates the application of the concept of the addition of a deep learning system to fractional calculus (FC) in order to accelerate and generalize the learning process. We propose a different form of neural network FGNN, Fractional Gradient Neural Network. In this network, the derivatives of fractional order are the gradient dynamics in control resulting in the optimisation being more fluid and the extraction of features being improved. The approach is a hybrid between the ease of use and memory capabilities of FC and the adaptation and data-driven capabilities of DL. The picture and signaling datasets experimental results indicate that these networks are more precise, more robust and less prone to overfitting as compared to standard networks. These findings indicate that FC is an excellent mathematical foundation to make next-generation deep learning models improved.
Zitieren
APA
Kokane, C. D., More, A. S., Sarode, H. J., Mokashi, M. K., Bhoite, S. P., & Bhandari, M. A. (2026). Fractional calculus applications in deep learning architectures. Journal of Interdisciplinary Mathematics, 29(3), 693-700. https://doi.org/10.47974/jim-2504
Vancouver
Kokane CD, More AS, Sarode HJ, Mokashi MK, Bhoite SP, Bhandari MA. Fractional calculus applications in deep learning architectures. Journal of Interdisciplinary Mathematics. 2026;29(3):693-700. doi:10.47974/jim-2504
BibTeX
@article{Kokane2026,
author = {Kokane, Chandrakant Deelip and More, Anjali S. and Sarode, Harsha Jitendra and Mokashi, Mandar K. and Bhoite, Sonali Prashant and Bhandari, Mahesh Ashok},
title = {Fractional calculus applications in deep learning architectures},
journal = {Journal of Interdisciplinary Mathematics},
year = {2026},
volume = {29},
number = {3},
pages = {693--700},
doi = {10.47974/jim-2504}
}
EUVIMED