Optimization in Artificial Intelligence and Deep Learning — Algorithms, Theory, and Practice
International Journal of Mathematics And Computer Research · 28.03.2026 · 14 (03)
DOI: 10.47191/ijmcr/v14ispc3.26 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Mathematics And Computer Research, online erschienen am 28.03.2026. Verfasst von Nikumbha Neha Ravindranath und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The core of machine learning and deep learning models relates to optimization. The present paper summarizes the principal categories of optimization algorithms in AI and deep learning and describes the mathematical concepts underpinning them in non-technical language, and relates these mathematical concepts to training recipes and engineering considerations. We discuss first-order stochastic algorithms (SGD and variations), adaptive algorithms (AdaGrad, RMProp, Adam)(4)(5) momentum and acceleration, second-order concepts and approximations (Newton, quasi-Newton, natural gradient, K-FAC), and recent issues like learning-rate schedules, batch normalization behavior, sharp vs. flat minima, generalization, and training large models. Pseudo code, best practice hyper parameters, and practical traps are given to ensure that this paper serves as both a conceptual primer, as well as a practical guide.
Zitieren
APA
Ravindranath, N. N., & Prasoon, K. P. (2026). Optimization in Artificial Intelligence and Deep Learning — Algorithms, Theory, and Practice. International Journal of Mathematics And Computer Research, 14(03). https://doi.org/10.47191/ijmcr/v14ispc3.26
Vancouver
Ravindranath NN, Prasoon KP. Optimization in Artificial Intelligence and Deep Learning — Algorithms, Theory, and Practice. International Journal of Mathematics And Computer Research. 2026;14(03). doi:10.47191/ijmcr/v14ispc3.26
BibTeX
@article{Ravindranath2026,
author = {Ravindranath, Nikumbha Neha and Prasoon, Kartha Pearly},
title = {Optimization in Artificial Intelligence and Deep Learning — Algorithms, Theory, and Practice},
journal = {International Journal of Mathematics And Computer Research},
year = {2026},
volume = {14},
number = {03},
doi = {10.47191/ijmcr/v14ispc3.26}
}
EUVIMED