A Theoretical Analysis of Joint Weight–Bias Hessian-Based Initialization Strategies in Deep Learning: Impact on Model Convergence, Curvature, and Accuracy
Journal of Advanced Research in Modeling and Simulation · 29.09.2026 · 8 (1) · 12-17
DOI: 10.24321/3117.4752.202601 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Research in Modeling and Simulation, online erschienen am 29.09.2026. Verfasst von Pratik Ahire.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Ahire, P. (2026). A Theoretical Analysis of Joint Weight–Bias Hessian-Based Initialization Strategies in Deep Learning: Impact on Model Convergence, Curvature, and Accuracy. Journal of Advanced Research in Modeling and Simulation, 8(1), 12-17. https://doi.org/10.24321/3117.4752.202601
Vancouver
Ahire P. A Theoretical Analysis of Joint Weight–Bias Hessian-Based Initialization Strategies in Deep Learning: Impact on Model Convergence, Curvature, and Accuracy. Journal of Advanced Research in Modeling and Simulation. 2026;8(1):12-17. doi:10.24321/3117.4752.202601
BibTeX
@article{Ahire2026,
author = {Ahire, Pratik},
title = {A Theoretical Analysis of Joint Weight–Bias Hessian-Based Initialization Strategies in Deep Learning: Impact on Model Convergence, Curvature, and Accuracy},
journal = {Journal of Advanced Research in Modeling and Simulation},
year = {2026},
volume = {8},
number = {1},
pages = {12--17},
doi = {10.24321/3117.4752.202601}
}
EUVIMED