Information Theory, Inference, and Learning Algorithms
by David J. C. MacKay
Publisher: Cambridge University Press 2003
ISBN/ASIN: 0521642981
ISBN-13: 9780521642989
Number of pages: 640
Description:
Information theory and inference, often taught separately, are here united in one entertaining textbook. These topics lie at the heart of many exciting areas of contemporary science and engineering - communication, signal processing, data mining, machine learning, pattern recognition, computational neuroscience, bioinformatics, and cryptography. 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.
Download or read it online for free here:
Download link
(multiple formats)
Similar books
Information and Codingby Karl Petersen - AMS
The aim is to review the many facets of information, coding, and cryptography, including their uses throughout history and their mathematical underpinnings. Prerequisites included high-school mathematics and willingness to deal with unfamiliar ideas.
(8078 views)
Conditional Rate Distortion Theoryby Robert M. Gray - Information Systems Laboratory
The conditional rate-distortion function has proved useful in source coding problems involving the possession of side information. This book represents an early work on conditional rate distortion functions and related theory.
(11511 views)
Network Coding Theoryby Raymond Yeung, S-Y Li, N Cai - Now Publishers Inc
A tutorial on the basics of the theory of network coding. It presents network coding for the transmission from a single source node, and deals with the problem under the more general circumstances when there are multiple source nodes.
(19036 views)
Around Kolmogorov Complexity: Basic Notions and Resultsby Alexander Shen - arXiv.org
Algorithmic information theory studies description complexity and randomness. This text covers the basic notions of algorithmic information theory: Kolmogorov complexity, Solomonoff universal a priori probability, effective Hausdorff dimension, etc.
(8805 views)