Information Theory, Inference, and Learning Algorithms
by David J. C. MacKay
Publisher: Cambridge University Press 2003
Number of pages: 640
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.
Home page url
Download or read it online for free here:
by Inder Jeet Taneja - Universidade Federal de Santa Catarina
Contents: Shannon's Entropy; Information and Divergence Measures; Entropy-Type Measures; Generalized Information and Divergence Measures; M-Dimensional Divergence Measures and Their Generalizations; Unified (r,s)-Multivariate Entropies; etc.
by 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.
by Neri Merhav - arXiv
Lecture notes for a graduate course focusing on the relations between Information Theory and Statistical Physics. The course is aimed at EE graduate students in the area of Communications and Information Theory, or graduate students in Physics.
by Venkatesan Guruswami, Atri Rudra, Madhu Sudan - University at Buffalo
Error-correcting codes are clever ways of representing data so that one can recover the original information even if parts of it are corrupted. The basic idea is to introduce redundancy so that the original information can be recovered ...