Information-Theoretic Methods in Data Science

This book provides a comprehensive and unified treatment of information theory and data science, covering topics such as signal acquisition, data compression, compressive sensing, data communication, representation learning, and emerging topics in statistics. It is written by leading experts in a clear and tutorial style, with consistent notation and definitions, and includes a topic overview, definition of key problems, emerging and open problems, and an extensive reference list. It is essential reading for graduate students and researchers in information theory, signal processing, machine learning, and statistics.

Format: Hardback
Length: 560 pages
Publication date: 08 April 2021
Publisher: Cambridge University Press

Discover the cutting-edge frontier at the intersection of information theory and data science with this comprehensive and unified treatment of the subject. Authored by renowned experts, this book offers a clear and tutorial-style approach, presenting information-theoretic methods in data acquisition, representation, analysis, and statistics, as well as machine learning. With a broad scope, it covers diverse topics such as signal acquisition, data compression, compressive sensing, data communication, representation learning, emerging statistics, and much more. Each chapter provides a comprehensive overview, outlines key problems, highlights emerging and open research areas, and includes an extensive reference list to facilitate in-depth knowledge and understanding. This essential resource serves as a thorough survey of the current research landscape and showcases the latest trends in information theory, signal processing, machine learning, and statistics. Whether you are a graduate student or a researcher in these fields, this book is a must-read for staying at the forefront of advancements.

Weight: 1078g
Dimension: 177 x 250 x 38 (mm)
ISBN-13: 9781108427135