Information Theory From Coding to Learning
- Textbook
Description
This enthusiastic introduction to the fundamentals of information theory builds from classical Shannon theory through to modern applications in statistical learning, equipping students with a uniquely well-rounded and rigorous foundation for further study. Introduces core topics such as data compression, channel coding, and rate-distortion theory using a unique finite block-length approach. With over 210 end-of-part exercises and numerous examples, students are introduced to contemporary applications in statistics, machine learning and modern communication theory. This textbook presents information-theoretic methods with applications…
- Add bookmark
- Cite
- Share
Key features
- Provides a systematic treatment of information-theoretic techniques in statistical learning and high-dimensional statistics
- Develops information theory for both continuous and discrete variables providing examples relevant to statistical and machine learning applications
- Focuses on finite block length (non-asymptotic) results, equipping students with information theory knowledge required for modern applications such as 6G and future network design
- Advanced material suitable for skipping on first reading is clearly indicated, enabling a fast introduction to fundamental concepts which can be enhanced with additional material on re-reading
About the book
- Subjects Communications and Signal Processing,Engineering,Statistical Theory and Methods,Statistics and Probability
- Format: Hardback
- Expected publication date: 30 November 2024
- ISBN: 9781108832908
- Dimensions (mm): 254 x 178 mm
- Page extent: 550 pages
- Availability: Not yet published - available from
- Format: Digital
- Expected publication date: 05 November 2024
- ISBN: 9781108966351