Information Theory for Data Science - Suh, Changho

. .

Résumé :
Information theory deals with mathematical laws that govern the flow, representation and transmission of information, just as the field of physics concerns laws that govern the behavior of the physical universe. The foundation was made in the context of communication while characterizing the fundamental limits of communication and offering codes (sometimes called algorithms) to achieve them. The most significant achievement of the field is the invention of digital communication which forms the basis of our daily-life digital products such as smart phones, laptops and any IoT devices. Recently it has also found important roles in a spotlight field that has been revolutionized during the past decades: data science. This book aims at demonstrating modern roles of information theory in a widening array of data science applications. The first and second parts of the book covers the core concepts of information theory: basic concepts on several key notions...

Biographie:
Dr. Changho Suh is an Associate Professor of Electrical Engineering at KAIST. He received the B.S. and M.S. degrees in Electrical Engineering from KAIST in 2000 and 2002 respectively, and the Ph.D. degree in Electrical Engineering and Computer Sciences from UC Berkeley in 2011. From 2011 to 2012, he was a postdoctoral associate at the Research Laboratory of Electronics in MIT. From 2002 to 2006, he was with Samsung Electronics.Prof. Suh is a recipient of numerous awards in research and teaching: the 2022 Google Research Award, the 2021 James L. Massey Research & Teaching Award for Young Scholars from the IEEE Information Theory Society, the 2020 LINKGENESIS Best Teacher Award (the campus-wide Grand Prize in Teaching), the 2019 AFOSR Grant, the 2019 Google Education Grant, the 2018 IEIE/IEEE Joint Award, the 2015 IEIE Haedong Young Engineer Award, the 2015 Bell Labs Prize finalist, the 2013 IEEE Communications Society Stephen O. Rice Prize, the 2011 David J. Sakrison Memorial Prize (the best dissertation award in UC Berkeley EECS), the 2009 IEEE ISIT Best Student Paper Award, and the five Department Teaching Awards (2013, 2019, 2020, 2021, 2022). Dr. Suh is an IEEE Fellow, a Distinguished Lecturer of the IEEE Information Theory Society from 2020 to 2022, the General Chair of the Inaugural IEEE East Asian School of Information Theory 2021, an Associate Head of the KAIST AI Institute from 2021 to 2022, and a Member of the Young Korean Academy of Science and Technology. He is also an Associate Editor of Machine Learning for IEEE TRANSACTIONS ON INFORMATION THEORY, a Guest Editor for the IEEE JOURNAL ON SELECTED AREAS IN INFORMATION THEORY, the Editor for IEEE INFORMATION THEORY NEWSLETTER, an Area Editor for IEEE BITS the Information Theory Magazine, an Area Chair of NeurIPS 2021-2022 and a Senior Program Committee of IJCAI 2019-2021....

Sommaire:
and celebrated source and channel coding theorems which concern the fundamental limits of communication. The last part focuses on applications that arise in data science, including social networks, ranking, and machine learning. The book is written as a text for senior undergraduate and graduate students working on Information Theory and Communications, and it should also prove to be a valuable reference for professionals and engineers from these fields....