AC51021 Probabilistic Inference and Machine Learning Mini Guide
For the full module guide see AC51021 full guide
Organisation
The Module Co-Ordinator for this module is Professor Stephen McKenna.
If you want to talk about an aspect of the module, or your work on it, please make an appointment to see one of the lecturer(s):
Professor Stephen McKenna, stephen@computing.dundee.ac.uk, 1.20 QMB
If you use email, please include "AC51021" in the heading.
Module Content and timetable
| Week | Topics Covered |
| One | Introduction to probability calculus, conditional independence and directed graphical models |
| Two | Expectations, multivariate distributions, introduction to sampling, Into to Matlab, |
| Three | Lab exercises |
| Four | Tutorial on problem sets |
| Five | Gaussians, mixtures, Bayesian learning, enumeration, Intro to Monte Carlo |
| Six | Learning with Markov chain Monte Carlo methods |
| Seven | Maximum likelihood learning: Gaussian, Gaussian mixtures (EM) |
| Eight | Factor graphs and the sum-product algorithm, hidden Markov models (EM) |
| Nine | Supervised learning, logistic regression, ML & MAP estimation |
| Ten | Learning using Laplace’s method and MCMC. Conclusions. |
| Eleven | Revision |
Assessment and Course-Work
The final degree exam counts for 100% of the final module mark.Resource List
Format: Title, Author, Publisher, ISBN.
Essential Titles
- Information Theory, Inference, and Learning Algorithms, David J C MacKay, Cambridge University Press 2003, 0-521-64298-1.
Recommended Titles
- Pattern Classification, Duda R O, Hart P E, Stork D G, Wiley 2001, 0-471-05669-3.
- Neural Networks for Pattern Recognition, Christopher M Bishop, Oxford University Press 1996, 0198538642 .
Background Reading
- Bayesian Data Analysis, Andrew Gelman, Chapman & Hall 2004, 158488388X.
- Probabilistic Modeling in Bioinformatics and Medical Informatics, Husmeier D, Dybowski R, Roberts S, Springer 2005, 1-85233-778-8.
- Bioinformatics: the machine learning approach, Baldi P and Brunak S, MIT Press 1998, 0-262-0244-X.
- The Elements of Statistical Learning, Hastie T, Tibshirani R, Friedman J, Springer 2003, 0387952845 .
- Principles of Data Mining, Hand D J, Mannila H and Smyth P, MIT Press 2001, 026208290X.
- Graphical Models for Machine Learning and Digital Communication, Brendan Frey, MIT Press 1998, 0-262-06202-X.
- Probability Theory: The Logic of Science, Edwin T Jaynes, Cambridge University Press 2003, 0521592712 .
- Learning Bayesian Networks, Richard E Neapolitan, Prentice Hall 2003, 0130125342 .
- Causality: Models, Reasoning and Inference, Judea Pearl, Cambridge University Press 2000, 0521773628 .
- Graphical Models: Foundations of Neural Computation, Jordon M I and Sejnowski T J (Eds.), MIT Press 2001, 0262600420 .
Module Specification
For the formal module specification see AC51021 Probabilistic Inference and Machine Learning 08-09.rtf