Information Theory, Inference & Learning Algorithms
Information theoryInferenceMachine LearningBayesianAprendizado computacional
4.0
Open LibraryFirst lines
You cannot do inference without making assumptions.
About this book
Book Jacket: > This textbook introduces theory in tandem with applications. Information theory is taught alongside practical communication systems, such as arithmetic coding for data compression and sparse-graph codes for error-correction. A toolbox of inference techniques, including message-passing algorithms, Monte Carlo methods, and variational approximations, are developed alongside applications of these tools to clustering, convolutional codes, independent component analysis, and neural networks. Publisher Description: > This textbook offers comprehensive coverage of Shannon's theory of information as well as the theory of neural networks and probabilistic data modelling. It includes explanations of Shannon's important source encoding theorem and noisy channel theorem as well as descriptions of practical data compression systems. Many examples and exercises make the book ideal for students to use as a class textbook, or as a resource for researchers who need to work with neural networks or state-of-the-art error-correcting codes.
Themes & subjects
Information theoryInferenceMachine LearningBayesianAprendizado computacionalInformation, Théorie de l'
About the author
David J.C. MacKay
April 22, 1967 – 14 April 2016
Professor of Natural Philosophy, Department of Physics, Cavendish Laboratory, University of Cambridge
Reviews
No reviews yet — be the first to write one from the Log screen.
Quotes
No quotes yet.
