Elements of Dimensionality Reduction and Manifold Learning

Dimensionality reduction, also known as manifold learning, is a machine learning area used to extract informative features from data for better representation and separation between classes. This book covers spectral, probabilistic, and neural network-based dimensionality reduction with geometric, probabilistic, and information-theoretic perspectives. It provides background and preliminaries on linear algebra, optimization, and kernels and applies to various applications like feature extraction, image processing, computer vision, and signal processing. The intended audiences are academics, students, and industry professionals, and it serves as a textbook, reference, and guidebook for feature extraction.

Format: Hardback
Length: 606 pages
Publication date: 03 February 2023
Publisher: Springer International Publishing AG

Dimensionality reduction, also referred to as manifold learning, is a crucial area within machine learning that focuses on extracting informative features from data to enhance its representation and facilitate the separation between classes. This comprehensive book provides a thorough review of both linear and nonlinear dimensionality reduction techniques, encompassing manifold learning. It delves into three primary aspects: spectral dimensionality reduction, probabilistic dimensionality reduction, and neural network-based dimensionality reduction. Each aspect is approached from distinct geometric, probabilistic, and information-theoretic perspectives, offering a comprehensive understanding of dimensionality reduction. To ensure a solid foundation, the book covers the necessary background and preliminaries in linear algebra, optimization, and kernels, providing a comprehensive grasp of the algorithms employed. These tools are then applied to diverse applications such as feature extraction, image processing, computer vision, and signal processing. This book appeals to a wide audience, including academics, students, and industry professionals seeking to delve into the intricacies of data extraction, transformation, and comprehension. It serves as a valuable textbook for machine learning and dimensionality reduction courses, offering comprehensive insights to academic researchers and students. Data scientists, machine learning scientists, computer vision scientists, and computer scientists can also rely on this book as a comprehensive reference. Additionally, statisticians involved in statistical learning and applied mathematicians specializing in manifolds and subspace analysis will find it immensely useful. Industry professionals, including applied engineers, data engineers, and engineers working in various fields of science that involve machine learning, can utilize this book as a practical guide for feature extraction from their data. By exploring the techniques and applications outlined in this book, readers will gain a deep understanding of the diverse methods employed in dimensionality reduction, enabling them to apply these strategies to their own data analysis and machine learning endeavors.

Weight: 1112g
Dimension: 235 x 155 (mm)
ISBN-13: 9783031106019
Edition number: 1st ed. 2023