Learning with Fractional Orthogonal Kernel Classifiers in Support Vector Machines: Theory, Algorithms and Applications

This book provides an overview of support vector algorithms from various perspectives, focusing on orthogonal kernel functions and their applications. It covers mathematical background, properties of kernel functions, and a tutorial on a Python package. The book also discusses the real-time and big data applications of support vector algorithms and presents a parallelizing procedure using CUDA. It offers insights for machine learning and scientific machine learning researchers to utilize fractional orthogonal kernel functions in pattern recognition and scientific computing problems.

Format: Hardback
Length: 305 pages
Publication date: 19 March 2023
Publisher: Springer Verlag, Singapore

This comprehensive book delves into the realm of support vector algorithms, offering a diverse range of perspectives on these powerful machine learning techniques. It begins by providing a solid mathematical foundation, covering essential concepts such as kernel functions, their properties, and their applications. The central focus of the book is on orthogonal kernel functions, which are extensively reviewed, including the classical kernel functions such as Chebyshev, Legendre, Gegenbauer, and Jacobi. Additionally, the fractional form of these kernel functions is introduced, offering practical insights for their usage.

To enhance convenience, a tutorial on a Python package named ORSVM is presented, enabling easy implementation of these kernel functions. Furthermore, the book showcases a wide array of applications for support vector algorithms, extending beyond classification to solving ordinary, partial, integro, and fractional differential equations.

In today's era of real-time and big data applications, the demand for support vector algorithms is on the rise. Recognizing this, the book presents a novel approach by parallelizing the procedure of support vector algorithms based on orthogonal kernel functions using the Compute Unified Device Architecture (CUDA). This enables efficient processing of large datasets, making support vector algorithms even more applicable in practical scenarios.

Moreover, the book offers valuable insights on how to utilize support vector algorithms based on orthogonal kernel functions in various situations, providing a comprehensive perspective to machine learning and scientific machine learning researchers worldwide. It encourages the exploration of fractional orthogonal kernel functions as a powerful tool for pattern recognition and scientific computing problems.

In summary, this comprehensive book serves as a valuable resource for anyone seeking to understand and apply support vector algorithms in their research or practical endeavors. It provides a solid mathematical foundation, explores orthogonal kernel functions in depth, and showcases a wide range of applications, making it an essential tool for practitioners in the field.

Weight: 647g
Dimension: 235 x 155 (mm)
ISBN-13: 9789811965524
Edition number: 1st ed. 2023