Support Vector Machines: Theory, Algorithms, and Applications

Jabardi, Mohammed (2025) Support Vector Machines: Theory, Algorithms, and Applications. INFOCOMMUNICATIONS JOURNAL, 17 (1). pp. 66-75. ISSN 20612079

Preview

Text InfocomJournal_2025_1_8_.pdf - Published Version Download (934kB) | Preview

Abstract

Support Vector Machines, or SVMs, are a strong group of supervised learning models that are commonly used for tasks like regression and classification. SVMs are based on the theory of statistical learning and try to find the best hyperplane that maximizes the gap between different classes. This makes it easier to apply to new data. Since kernel functions are used with SVMs, they are more flexible and can handle both linear and nonlinear situations well. Even though they have a strong theoretical base, they still face problems in the real world, like being hard to code and difficult to tune parameters, especially for big datasets. Recent improvements, like scalable solvers and estimated kernel methods, have made them a lot more useful. This essay talks about SVM theory, its main algorithms, and how it is used in the real world. It shows how it is used in bioinformatics, banking, and image processing, among other areas.

Actions (login required)

Edit Item