An Introduction to Artificial Intelligence Based on Reproducing Kernel Hilbert Spaces

This textbook provides an in-depth exploration of statistical learning with reproducing kernels, demonstrating how they can be used to design and justify kernel learning algorithms in artificial intelligence. It also offers two biomedical applications and analyzes a large class of algorithms, making it an ideal resource for graduate and postgraduate courses in computational mathematics and data science.

Format: Paperback / softback
Length: 152 pages
Publication date: 18 May 2022
Publisher: Springer Nature Switzerland AG

This comprehensive textbook delves into the realm of statistical learning with reproducing kernels, an active area of research that holds immense potential in unraveling trends associated with deep neural networks. The author adeptly showcases how the concept of reproducing kernel Hilbert Spaces (RKHS), coupled with tools from regularization theory, can be effectively employed in the design and justification of kernel learning algorithms, which have the capability to address a wide range of problems in the field of artificial intelligence. Furthermore, the book offers a detailed account of two biomedical applications of the considered algorithms, providing tangible evidence of how closely the theory aligns with practical implementation.

One of the notable features of this textbook is its comprehensive analysis of a vast class of algorithms within the realm of learning theory. This encompasses a wide range of linear regularization schemes, including Tikhonov regularization as a specific case. By examining these algorithms through a unified theoretical framework, rather than treating them separately, the presentation becomes streamlined and more accessible to readers.

An Introduction to Artificial Intelligence Based on Reproducing Kernel Hilbert Spaces serves as an invaluable resource for graduate and postgraduate courses in computational mathematics and data science. It provides a solid foundation in the theoretical aspects of reproducing kernel Hilbert Spaces, regularization theory, and kernel learning algorithms, equipping students with the knowledge and tools necessary to excel in this rapidly evolving field.

Weight: 322g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030983154
Edition number: 1st ed. 2022