Information theory, inference, and learning algorithms

'This is an extraordinary and important book, generous with insight and rich with detail in statistics, information theory, and probabilistic modeling across a wide swathe of standard, creatively original, and delightfully quirky topics. David MacKay is an uncompromisingly lucid thinker, from whom students, faculty and practitioners all can learn.' Peter Dayan and Zoubin Ghahramani, Gatsby Computational Neuroscience Unit, University College, London 'This is primarily an excellent textbook in the areas of information theory, Bayesian inference and learning algorithms. Undergraduates and postgraduates students will find it extremely useful for gaining insight into these topics; however, the book also serves as a valuable reference for researchers in these areas. Both sets of readers should find the book enjoyable and highly useful.' David Saad, Aston University 'An utterly original book that shows the connections between such disparate fields as information theory and coding, inference, and statistical physics.' Dave Forney, Massachusetts Institute of Technology 'An instant classic, covering everything from Shannon's fundamental theorems to the postmodern theory of LDPC codes. You'll want two copies of this astonishing book, one for the office and one for the fireside at home.' Bob McEliece, California Institute of Technology '... a quite remarkable work ... the treatment is specially valuable because the author has made it completely up-to-date ... this magnificent piece of work is valuable in introducing a new integrated viewpoint, and it is clearly an admirable basis for taught courses, as well as for self-study and reference. I am very glad to have it on my shelves.' Robotica 'With its breadth, accessibility and handsome design, this book should prove to be quite popular. Highly recommended as a primer for students with no background in coding theory, the set of chapters on error correcting codes are an excellent brief introduction to the elements of modern sparse graph codes: LDPC, turbo, repeat-accumulate and fountain codes are described clearly and succinctly.' IEEE Transactions on Information Theory "...a valuable reference...enjoyable and highly useful." American Scientist "...an impressive book, intended as a class text on the subject of the title but having the character and robustness of a focused encyclopedia. The presentation is finely detailed, well documented, and stocked with artistic flourishes." Mathematical Reviews "Essential reading for students of electrical engineering and computer science; also a great heads-up for mathematics students concerning the subtlety of many commonsense questions." Choice "An utterly original book that shows the connections between such disparate fields as information theory and coding, inference, and statistical physics." Dave Forney, Massachusetts Institute of Technology "This is an extraordinary and important book, generous with insight and rich with detail in statistics, information theory, and probabilistic modeling across a wide swathe of standard, creatively original, and delightfully quirky topics. David MacKay is an uncompromisingly lucid thinker, from whom students, faculty and practitioners all can learn." Peter Dayan and Zoubin Ghahramani, Gatsby Computational Neuroscience Unit, University College, London "An instant classic, covering everything from Shannon's fundamental theorems to the postmodern theory of LDPC codes. You'll want two copies of this astonishing book, one for the office and one for the fireside at home." Bob McEliece, California Institute of Technology "An excellent textbook in the areas of infomation theory, Bayesian inference and learning alorithms. Undergraduate and post-graduate students will find it extremely useful for gaining insight into these topics." REDNOVA "Most of the theories are accompanied by motivations, and explanations with the corresponding examples...the book achieves its goal of being a good textbook on information theory." ACM SIGACT News Read more...