# Probabilistic Modelling and Reasoning

Note: The course and homepage will be updated in autumn 2017. The content will generally be similar to the 2016/17 course.
DRPS course descriptor | Informatics course page

2016/17 course information below

## Introduction to the Course

Probabilistic Modelling and Reasoning covers the foundations of probabilistic modelling in a machine learning context. It examines probabilistic models in a supervised and unsupervised settings and the application of probabilistic modelling in many unsupervised modelling scenarios. On this course we will cover structured probabilistic models via undirected and directed graphical models, and computation with probabilities through using those graphical model structures. We will cover a variety of distributions that may be used in these settings. We will look at temporal models, including hidden Markov models and linear state space models, and compositional methods including mixture models and products. Deep learning methods utilising Boltzmann machines will also be discussed.

The course details can be found here. The introductory handout for the course is available.

There is an assignment for this course. The assignment deadline is on the course descriptor. The coursework will be available approximately 3 weeks before the deadline.

MATHS PREREQUSITES: To do PMR you need a reasonable background in statistics, calculus, linear algebra. Please check the course descriptor. You should also thoroughly review the maths in the following cribsheet (from Iain Murray) before the start of the course, and attempt the tut0.pdf sheet. A handout on Mathematical Preliminaries which used to be used for the course LfD1 is also useful for PMR; all material is relevant.

## Lectures

PMR lectures will be in Semester 2. They can be accessed via the link at the top of the page. See the Teaching Timetables for timing and location information.

## Resources

Books. The course textbook is Bayesian Reasoning and Machine Learning by David Barber (Cambridge University Press, 2012; free online version available). I'd really advise buying this. You will find everything much easier if you have a physical copy.

It is well worth having a probability text book by your side to complement this. My favourite is Probability and Random Processes by Grimmett and Stirzaker, now in its third edition. You should be able to pick up a good value second hand copy if you are short of cash.

The Matrix Cookbook is also a handy resource to have available.