Open Access
·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667
Powered by:DOICrossrefiThenticate
The Journal of Information and Optimization Sciences (JIOS) is a world leading journal publishing high quality, rigorously peer-reviewed original research in all mathematically-oriented theoretical and applied topics in information sciences, optimization sciences and related areas since 1980. Subjects include but are not limited to:
• Information Sciences
• Optimization Sciences
• Control Theory
• Operational Research
• Decision Sciences
• Information Theory
• Information Technology
• Computer Networks and Communications
• Mathematical Programming
• Modelling and Simulation
• Database Management
• Applications to Engineering Sciences
• Applications to Technology
Issues up to 2022 co-published with and available at:
Mathematical foundations of neural network weight optimization
*Madhuri B. ThoratCorresponding authorthoratmadhuri31@gmail.comDepartment of Computer Science and Engineering College of Engineering Bharti Vidyapeeth (Deemed to be University) Pune, Maharashtra, 411043, IndiaView full profile →
, Vaishali Pawan Wawagevaishali.wawage@vit.eduDepartment of Engineering Science and Humanities Vishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile →
, Durga Prasad Yadavdurga.prasad@niu.edu.inSchool of Engineering & Technology Noida International UniversityNoida, Uttar Pradesh, 203201, IndiaView full profile →
, P. Pushpalathapushpalatha@gmail.comDepartment of Computer Science Meenakshi College of Arts and Science Meenakshi Academy of Higher Education and ResearchChennai, Tamil Nadu, 600078, IndiaView full profile →
, Yatin Gandhigyatin33@gmail.comCompetent SoftwaresPune, Maharashtra, 411038, IndiaView full profile →
* Corresponding author · click or hover a name for details
Neural network optimisation is a major problem in deep learning. It needs algorithms that work well with millions of parameters and keep convergence stable and generalisation. Stochastic gradient descent (SGD) and other traditional first-order methods are fast to compute, but they take a long time to converge and are sensitive to learning rate schedules. Second-order methods use curvature information to speed up optimisation, but they are too expensive for large networks. Adaptive methods like Adam and RMSProp are more stable and converge faster, but they don’t always work as well as SGD. In this paper presents a thorough mathematical examination of weight optimisation in neural networks, encompassing gradient-based methods, regularisation techniques, theoretical perspectives on loss landscapes, and comparative performance evaluations.
[1] J. P. Selvan and G. P. Potdar, “Calculation of neural network weights and biases using particle swarm optimization,” Engineering Proceedings, vol. 59, p. 190 (2023), doi: 10.3390/engproc2023059190.[2] J. Bedi, A. Anand, S. Godara, R. S. Bana, M. A. Faiz, S. Marwaha, and R. Parsad, “Effective weight optimization strategy for precise deep learning forecasting models using EvoLearn approach,” Scientific Reports, vol. 14, p. 20139 (2024), doi: 10.1038/s41598-024-69325-3.[3] F. Marchetti, S. Guastavino, C. Campi, F. Benvenuto, and M. Piana, “A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metrics,” Optimization Letters, vol. 19, pp. 169–192 (2025), doi: 10.1007/s11590-024-02112-1. [4] D. Chung and I. Sohn, “Neural network optimization based on complex network theory: A survey,” Mathematics, vol. 11, p. 321 (2023), doi: 10.3390/math11020321.[5] R. Agarwal, R. P. Chaturvedi, A. Mishra, S. Asthana, and M. Parashar, “An approach for determining the best solution for intuitionistic fuzzy transportation problem,” Journal of Information and Optimization Sciences, vol. 45, no. 7, pp. 1867–1879 (2024), doi: 10.47974/JIOS-1739.[6] F. Cao, X. Guo, X. Dong, and D. Yuan, “wbPINN: Weight balanced physics-informed neural networks for multi-objective learning,” Applied Soft Computing, vol. 170, p. 112632 (2025), doi: 10.1016/j.asoc.2024.112632.[7] U. Waqas, M. F. Ahmed, H. M. A. Rashid, and M. E. Al-Atroush, “Optimization of neural-network model using a meta-heuristic algorithm for the estimation of dynamic Poisson’s ratio of selected rock types,” Scientific Reports, vol. 13, p. 11089 (2023), doi:10.1038/s41598-023-38163-0.[8] L. Gonbadi, H. Rostami, E. Sahafizadeh, S. Rostami, M. M. Nejad, and A. Shirzadi, “Input driven optimization of echo state network parameters for prediction on chaotic time series,” Scientific Reports, vol. 15, p. 33005 (2025), doi: 10.1038/s41598-025-18261-x. [9] D. Goyal, A. Kumar, Y. Gandhi, and V. Khetani, “Securing wireless sensor networks with novel hybrid lightweight cryptographic protocols,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 703–714 (2024).[10] S. Anjum, A. Ahmed, R. Kurup, S. Kidiya, and S. Kureshi, “Blockchain based image steganography,” International Journal of Advanced Computer Theory and Engineering (IJACTE), vol. 14, no. 1, pp. 147–152 (May 2025).
Views: 54Downloads: 6Citations: 0
Install Journal of Information and Optimization SciencesFaster access from your home screen
