Information theory, inference, and learning algorithms

Information theory, inference, and learning algorithms Information theory and inference, often taught separately, are hereunited in one entertaining textbook. These topics lie at the heart ofmany exciting areas of contemporary science and engineering -communication, signal processing, data mining, machine learning,pattern recognition, computational neuroscience, bioinformatics, andcryptography. This textbook introduces theory in tandem withapplications. Information theory is taught alongside practicalcommunication systems, such as arithmetic coding for data compressionand sparse-graph codes for error-correction. A toolbox of inferencetechniques, including message-passing algorithms, Monte Carlomethods, and variational approximations, are developed alongsideapplications of these tools to clustering, convolutional codes,independent component analysis, and neural networks. The final partof the book describes the state of the art in error-correcting codes,including low-density parity-check codes, turbo codes, and digitalfountain codes — the twenty-first century standards for satellitecommunications, disk drives, and data broadcast. Richly illustrated,filled with worked examples and over 400 exercises, some withdetailed solutions, David MacKay's groundbreaking book is ideal forself-learning and for undergraduate or graduate courses. Interludeson crosswords, evolution, and sex provide entertainment along theway. In sum, this is a textbook on information, communication, andcoding for a new generation of students, and an unparalleled entrypoint into these subjects for professionals in areas as diverse ascomputational biology, financial engineering, and machine learning.

Authors: MacKay D.J.C.Pages: 640     Year: 2003

Tags: algorithms inference information theory learning

Customers who bought this item also bought:


© 2007–2017 Dleex.

English      German      French      Russian

For any question please write to our email e-mail