EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A New Generalization of Gradient Method with Penalty and Momentum Terms for Wavelet Feedforward Neural Networks

Khidir Shaib Mohamed, Alawia Adam, Sofian A. A. Saad, Naglaa Mohammed, Ahmed Himadan

Mathematics · 10.06.2026 · 14 (12) · 2078

DOI: 10.3390/math14122078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 10.06.2026. Verfasst von Khidir Shaib Mohamed und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qassim University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Regularization plans, acceleration mechanisms, and optimization strategies all have a significant impact on the convergence behavior of neural network training algorithms. A thorough analysis of a batch gradient method (BGM) improved with momentum and penalty terms for training wavelet feedforward neural networks (WFNNs) is presented in this research. In nonlinear function approximation challenges, the suggested approach seeks to enhance convergence speed, stability, and generalization performance. To prove the monotonicity, weak convergence, and strong convergence of the training process under the combined influence of momentum regularization and penalty, a rigorous mathematical framework is created. While the momentum term speeds up convergence by reducing oscillations in the gradient trajectory, the penalty term suppresses weight overgrowth and overfitting. The algorithm is applied to the Peaks function, Sinc function, and 5-bit parity problem to support these theoretical findings. The findings show that in terms of quicker convergence, lower mean squared error (MSE), and smaller gradient norms, the suggested BGM with penalty and momentum performs better than traditional BGM with L2 regularization. Smoother optimization dynamics and improved generalization are revealed by the training convergence and gradient norm evolution curves. The suggested method offers a cohesive viewpoint on integrating momentum acceleration, regularization, and penalty into gradient-based optimization for WFNNs. It is a promising technique for function approximation, pattern recognition, and control system applications since it provides both theoretical convergence guarantees and real-world increases in learning efficiency.

Förderung

  • Qassim University

Zitieren

APA

Mohamed, K. S., Adam, A., Saad, S. A. A., Mohammed, N., & Himadan, A. (2026). A New Generalization of Gradient Method with Penalty and Momentum Terms for Wavelet Feedforward Neural Networks. Mathematics, 14(12), 2078. https://doi.org/10.3390/math14122078

Vancouver

Mohamed KS, Adam A, Saad SAA, Mohammed N, Himadan A. A New Generalization of Gradient Method with Penalty and Momentum Terms for Wavelet Feedforward Neural Networks. Mathematics. 2026;14(12):2078. doi:10.3390/math14122078

BibTeX
@article{Mohamed2026,
  author = {Mohamed, Khidir Shaib and Adam, Alawia and Saad, Sofian A. A. and Mohammed, Naglaa and Himadan, Ahmed},
  title = {A New Generalization of Gradient Method with Penalty and Momentum Terms for Wavelet Feedforward Neural Networks},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {12},
  pages = {2078},
  doi = {10.3390/math14122078}
}
Kostenlos starten →