Mackay Information Theory Inference Learning Algorithms - Info and Reading Options

The Internet Archive:

This is an outstanding book by Prof. David MacKay (of U. of Cambridge). It is downloadable from author's web page: <a href="http://www.inference.phy.cam.ac.uk/mackay/" rel="nofollow">http://www.inference.phy.cam.ac.uk/mackay/</a>.<br /><br />Please spread the word, and tell your profs to use this free book in their courses.<br /><br />This is an e-book free to read and share electronically as indicated so by the author. However, you are not allowed to print the whole book, instead you should order it from the publisher.<br /><br /><b>Copyright Cambridge University Press 2003. On-screen viewing permitted. Printing not permitted. http://www.cambridge.org/0521642981<br />You can buy this book for 30 pounds or $50. See http://www.inference.phy.cam.ac.uk/mackay/itila/ for links.<br /></b><br />Contents<br /><br />Preface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v<br />1 Introduction to Information Theory . . . . . . . . . . . . . 3<br />2 Probability, Entropy, and Inference . . . . . . . . . . . . . . 22<br />3 More about Inference . . . . . . . . . . . . . . . . . . . . . 48<br />I Data Compression . . . . . . . . . . . . . . . . . . . . . . 65<br />4 The Source Coding Theorem . . . . . . . . . . . . . . . . . 67<br />5 Symbol Codes . . . . . . . . . . . . . . . . . . . . . . . . . 91<br />6 Stream Codes . . . . . . . . . . . . . . . . . . . . . . . . . . 110<br />7 Codes for Integers . . . . . . . . . . . . . . . . . . . . . . . 132<br /><br />II Noisy-Channel Coding . . . . . . . . . . . . . . . . . . . . 137<br />8 Dependent Random Variables . . . . . . . . . . . . . . . . . 138<br />9 Communication over a Noisy Channel . . . . . . . . . . . . 146<br />10 The Noisy-Channel Coding Theorem . . . . . . . . . . . . . 162<br />11 Error-Correcting Codes and Real Channels . . . . . . . . . 177<br /><br />III Further Topics in Information Theory . . . . . . . . . . . . . 191<br />12 Hash Codes: Codes for Efficient Information Retrieval . . 193<br />13 Binary Codes . . . . . . . . . . . . . . . . . . . . . . . . . 206<br />14 Very Good Linear Codes Exist . . . . . . . . . . . . . . . . 229<br />15 Further Exercises on Information Theory . . . . . . . . . . 233<br />16 Message Passing . . . . . . . . . . . . . . . . . . . . . . . . 241<br />17 Communication over Constrained Noiseless Channels . . . 248<br />18 Crosswords and Codebreaking . . . . . . . . . . . . . . . . 260<br />19 Why have Sex? Information Acquisition and Evolution . . 269<br /><br />IV Probabilities and Inference . . . . . . . . . . . . . . . . . . 281<br />20 An Example Inference Task: Clustering . . . . . . . . . . . 284<br />21 Exact Inference by Complete Enumeration . . . . . . . . . 293<br />22 Maximum Likelihood and Clustering . . . . . . . . . . . . . 300<br />23 Useful Probability Distributions . . . . . . . . . . . . . . . 311<br />24 Exact Marginalization . . . . . . . . . . . . . . . . . . . . . 319<br />25 Exact Marginalization in Trellises . . . . . . . . . . . . . . 324<br />26 Exact Marginalization in Graphs . . . . . . . . . . . . . . . 334<br />27 Laplace’s Method . . . . . . . . . . . . . . . . . . . . . . . 341<br />28 Model Comparison and Occam’s Razor . . . . . . . . . . . 343<br />29 Monte Carlo Methods . . . . . . . . . . . . . . . . . . . . . 357<br />30 Efficient Monte Carlo Methods . . . . . . . . . . . . . . . . 387<br />31 Ising Models . . . . . . . . . . . . . . . . . . . . . . . . . . 400<br />32 Exact Monte Carlo Sampling . . . . . . . . . . . . . . . . . 413<br />33 Variational Methods . . . . . . . . . . . . . . . . . . . . . . 422<br />34 Independent Component Analysis and Latent Variable Mod-<br />elling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 437<br />35 Random Inference Topics . . . . . . . . . . . . . . . . . . . 445<br />36 Decision Theory . . . . . . . . . . . . . . . . . . . . . . . . 451<br />37 Bayesian Inference and Sampling Theory . . . . . . . . . . 457<br /><br />V Neural networks . . . . . . . . . . . . . . . . . . . . . . . . 467<br />38 Introduction to Neural Networks . . . . . . . . . . . . . . . 468<br />39 The Single Neuron as a Classifier . . . . . . . . . . . . . . . 471<br />40 Capacity of a Single Neuron . . . . . . . . . . . . . . . . . . 483<br />41 Learning as Inference . . . . . . . . . . . . . . . . . . . . . 492<br />42 Hopfield Networks . . . . . . . . . . . . . . . . . . . . . . . 505<br />43 Boltzmann Machines . . . . . . . . . . . . . . . . . . . . . . 522<br />44 Supervised Learning in Multilayer Networks . . . . . . . . . 527<br />45 Gaussian Processes . . . . . . . . . . . . . . . . . . . . . . 535<br />46 Deconvolution . . . . . . . . . . . . . . . . . . . . . . . . . 549<br /><br />VI Sparse Graph Codes . . . . . . . . . . . . . . . . . . . . . 555<br />47 Low-Density Parity-Check Codes . . . . . . . . . . . . . . 557<br />48 Convolutional Codes and Turbo Codes . . . . . . . . . . . . 574<br />49 Repeat–Accumulate Codes . . . . . . . . . . . . . . . . . . 582<br />50 Digital Fountain Codes . . . . . . . . . . . . . . . . . . . . 589<br /><br />VII Appendices . . . . . . . . . . . . . . . . . . . . . . . . . . 597<br />A Notation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 598<br />B Some Physics . . . . . . . . . . . . . . . . . . . . . . . . . . 601<br />C Some Mathematics . . . . . . . . . . . . . . . . . . . . . . . 605<br />Bibliography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 613<br />Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 620<br /><br />

Search for “Mackay Information Theory Inference Learning Algorithms” downloads:

Visit our Downloads Search page to see if downloads are available.

Find “Mackay Information Theory Inference Learning Algorithms” in Libraries Near You:

Read or borrow “Mackay Information Theory Inference Learning Algorithms” from your local library.

• The WorldCat Libraries Catalog: Find a copy of “Mackay Information Theory Inference Learning Algorithms” at a library near you.