Fractional calculus applications in deep learning architectures

Kokane, Chandrakant Deelip; More, Anjali S.; Sarode, Harsha Jitendra; Mokashi, Mandar K.; Bhoite, Sonali Prashant; Bhandari, Mahesh Ashok

doi:10.47974/JIM-2504

Open Access Research Article

Fractional calculus applications in deep learning architectures

Chandrakant Deelip Kokanecdkokane1992@gmail.comDepartment of Computer Science and Engineering (Artificial Intelligence)Vishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile → , Anjali S. Moreanjali.dalvi@sitpune.edu.inDepartment of Artificial Intelligence and Machine LearningSymbiosis International (Deemed University)Symbiosis Institute of TechnologyPune, Maharashtra, 412115, IndiaView full profile → , ^*Harsha Jitendra SarodeCorresponding authorsarodeharsha28@gmail.comDepartment of Electronics and Telecommunications EngineeringNutan Maharashtra Institute of Engineering and TechnologyPune, Maharashtra, 410507, IndiaView full profile → , Mandar K. Mokashimandar.mokashi16@gmail.comDepartment of Computer Science and EngineeringSchool of Computing(Artificial Intelligence and Analytics)MIT-ADT UniversityPune, Maharashtra, 412201, IndiaView full profile → , Sonali Prashant Bhoitesonalibhoite7@gmail.comDepartment of Information TechnologyVishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile → , Mahesh Ashok Bhandarimahesh.bhandari@vit.eduDepartment of Information TechnologyVishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 693–700Vol. 29Issue 3March 2026DOI: 10.47974/JIM-2504XML

Received:: 01 Apr 2025
Published Online:: 18 Mar 2026
Article type:: Research Article
Language:: EN
Article no.:: JIM-2504
Pages:: 693–700

Abstract

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.

Keywords

Fractional calculus Deep learning Fractional gradient neural network (FGNN)Optimization Generalization Convergence stability

Subject Classifications

26A3368T07

References

[1] C. Coelho, M. F. P. Costa, and L. L. Ferrás, “Fractional calculus meets neural networks for computer vision: A survey,” AI, vol. 5, pp. 1391–1426 (2024).
[2] İ. Avcı, H. Lort, and B. E. Tatlıcıoğlu, “Numerical investigation and deep learning approach for fractal–fractional order dynamics of Hopfield neural network model,” Chaos, Solitons & Fractals, vol. 177, pp. 114302 (2023).
[3] T. Allahviranloo, A. Jafarian, and R. Saneifard, “An application of artificial neural networks for solving fractional higher-order linear integro-differential equations,” Boundary Value Problems, vol. 2023, no. 74 (2023).
[4] Bolla Sai Durga Prasanna and Chiraparapu Srinivasa Rao, “Village Development System using Greedy Algorithm,” International Journal for Interdisciplinary Sciences and Engineering Applications, Volume 6, Issue 3, pp. 12–19 (2025), doi: 10.5281/zenodo.16728954
[5] M. Joshi, S. Bhosale, and V. A. Vyawahare, “A survey of fractional calculus applications in artificial neural networks,” Artificial Intelligence Review, vol. 56, no. 11, pp. 13897–13950 (Nov. 2023). doi: 10.1007/s10462-023-10474-8.
[6] Y. Ma and W. Li, “Application and research of fractional differential equations in dynamic analysis of supply chain financial chaotic system,” Chaos, Solitons & Fractals, vol. 130, pp. 109417 (2020).
[7] R. D. Mohanraj and C. Rajesh, “Fixed point results using self mapping in multiplicative metric space,” Journal of Interdisciplinary Mathematics, vol. 28, no. 5, pp. 1723–1734 (2025). doi: 10.47974/JIM-2142.
[8] P. S. Togrikar, S. F. Firoj, R. P. Balaso, and J. D. Abhimanyu, “Energy Safe Pro: A smart and secure prepaid metering solution for energy management,” International Journal of Advanced Computer Engineering and Communication Technology (IJACECT), vol. 13, no. 2, pp. 39–43 (Mar. 2025).
[9] V. Deshpande, D. Khubalkar, A. Dhablia, M. J. Pasha, D. Dhabliya, and Y. Gandhi, “Enhancing financial transaction security with lightweight cryptographic algorithms,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 741–751 (2024).
[10] M. G. Dhote, B. M. Nanche, P. N. Mahalle, S. S. Ali, M. Gulhane, and V. S. Karwande, “Deep learning for optimized path planning in autonomous vehicles by integrating reinforcement learning with convolutional neural networks,” Journal of Information and Optimization Sciences, vol. 46, no. 4-B, pp. 1129–1139 (2025).

Views: 202Downloads: 113Citations: 0