Have a personal or library account? Click to login
Accelerating Neural Network Training with FSGQR: A Scalable and High-Performance Alternative to Adam Cover

Accelerating Neural Network Training with FSGQR: A Scalable and High-Performance Alternative to Adam

Journal of Artificial Intelligence and Soft Computing Research
Volume 15 (2025): Issue 2 (March 2025)
By: Jarosław Bilski,  Bartosz Kowalczyk,  Ludmila Dymova and  Min Xiao  
Open Access
|Feb 2025

Authors

Jarosław Bilski

jaroslaw.bilski@pcz.pl

Department of Artificial Intelligence, Częstochowa University of Technology, Częstochowa, Poland

Bartosz Kowalczyk

Department of Artificial Intelligence, Częstochowa University of Technology, Częstochowa, Poland

Ludmila Dymova

Information Technology Institute, SAN University, Łódź, Poland

Min Xiao

College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing, China
DOI: https://doi.org/10.2478/jaiscr-2025-0006
Journal RSS Feed
Language: English
Page range: 95 - 113
Submitted on: Sep 7, 2024
Accepted on: Dec 4, 2024
Published on: Feb 5, 2025
Published by: SAN University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
neural network training algorithm, QR decomposition, scaled Givens rotations, approximation, classification
Related subjects:
Computer sciences,
Artificial intelligence,
Databases and data mining

© 2025 Jarosław Bilski, Bartosz Kowalczyk, Ludmila Dymova, Min Xiao, published by SAN University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 15 (2025): Issue 2 (March 2025)Next article