Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Control Systems and Optimization Letters
K. Karthick
GMR Institute of Technology
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comprehensive Overview of Optimization Techniques in Machine Learning Training K. Karthick
Control Systems and Optimization Letters Vol 2, No 1 (2024)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/csol.v2i1.69

Abstract

This article offers a comprehensive overview of optimization techniques employed in training machine learning (ML) models. Machine learning, a subset of artificial intelligence, employs statistical methods to enable systems to learn and improve from experience without explicit programming. The paper delineates the significance of optimization in ML, emphasizing its role in adjusting model parameters to minimize loss functions, thereby ensuring efficient model training and improved generalization. The discussion encompasses various optimization methods, including Gradient Descent Variants, Adaptive Learning Rate Methods, Second-Order Optimization Methods, Regularization Methods, Constraint-based Methods, and Bayesian Optimization. Each section elucidates the principles, applications, and benefits of these techniques, highlighting their relevance in addressing challenges such as overfitting, scalability, and computational efficiency. The article aims to guide researchers, practitioners, and enthusiasts in navigating the complex landscape of optimization techniques tailored for diverse machine learning algorithms and applications.
Co-Authors