- ARCHIVE for reference only

University Homepage
DRPS Homepage
DRPS Search
DRPS Contact
DRPS : Course Catalogue : School of Informatics : Informatics

Postgraduate Course: Probabilistic Modelling and Reasoning (INFR11050)

Course Outline
SchoolSchool of Informatics CollegeCollege of Science and Engineering
Course typeStandard AvailabilityAvailable to all students
Credit level (Normal year taken)SCQF Level 11 (Postgraduate) Credits10
Home subject areaInformatics Other subject areaNone
Course website Taught in Gaelic?No
Course descriptionWhen dealing with real world data, we often need to deal with uncertainty. For example, short segments of a speech signal are ambiguous, and we need to take into account context in order to make sense of an utterance. Probability theory provides a rigorous method for representing and reasoning with uncertain knowledge. The course covers two main areas (i) the process of inference in probabilistic reasoning systems and (ii) learning probabilistic models from data. Its aim is to provide a firm grounding in probabilistic modelling and reasoning, and to give a basis which will allow students to go on to develop their interests in more specific areas, such as data-intensive linguistics, automatic speech recognition, probabilistic expert systems, statistical theories of vision etc.
Entry Requirements (not applicable to Visiting Students)
Pre-requisites Co-requisites
Prohibited Combinations Other requirements This course has the following mathematics prerequisites:

1 - Probability theory: Discrete and continuous univariate random variables. Expectation, variance. Univariate Gaussian distribution. Joint and conditional distributions. (At the level taught in MfI 1&4).

2 - Linear algebra: Vectors and matrices: definitions, addition. Matrix multiplication, matrix inversion. Eigenvectors, determinants, quadratic forms. (At the level taught in MfI 2&3).

3 - Calculus: Functions of several variables. Partial differentiation. Multivariate maxima and minima. Integration: need to know definitions, including multivariate integration. (At the level taught in MfI 1&2)

4 - Special functions: Log, exp are fundamental. (At the level taught in MfI 1)

5 - Geometry: Basics of lines, planes and hyperplanes. Coordinate geometry of circle, sphere, ellipse, ellipsoid and n-dimensional generalizations. (At level taught in MfI 1&4)
Additional Costs None
Information for Visiting Students
Displayed in Visiting Students Prospectus?Yes
Course Delivery Information
Delivery period: 2011/12 Semester 1, Available to all students (SV1) WebCT enabled:  No Quota:  None
Location Activity Description Weeks Monday Tuesday Wednesday Thursday Friday
CentralLecture1-11 10:00 - 10:50
CentralLecture1-11 10:00 - 10:50
First Class Week 1, Tuesday, 10:00 - 10:50, Zone: Central. Bristo Sq 7 LT1
Exam Information
Exam Diet Paper Name Hours:Minutes
Main Exam Diet S2 (April/May)2:00
Delivery period: 2011/12 Semester 1, Part-year visiting students only (VV1) WebCT enabled:  No Quota:  None
Location Activity Description Weeks Monday Tuesday Wednesday Thursday Friday
CentralLecture1-11 10:00 - 10:50
CentralLecture1-11 10:00 - 10:50
First Class Week 1, Tuesday, 10:00 - 10:50, Zone: Central. Bristo Sq 7 LT1
Exam Information
Exam Diet Paper Name Hours:Minutes
Main Exam Diet S1 (December)2:00
Summary of Intended Learning Outcomes
1 - Define the joint distribution implied by directed and undirected probabilistic graphical models.
2 - Carry out inference ingraphical models from first principles by hand, and by using the junction tree algorithm.
3 - Demonstrate understanding of maximum likelihood and Bayesian methods for parameter estimation by hand derivation of estimation equations for specific problems.
4 - Critically discuss differences between various latent variable models for data.
5 - Derive EM updates for various latent variable models (e.g. mixture models).
6 - Define entropy, joint entropy, conditional entropy, mutual information, expected code length.
7 - Demonstrate ability to design, assess and evaluate belief network models.
8 - Use belief network packages (e.g. JavaBayes) and matlab code for probabilistic graphical models.
9 - Demonstrate ability to conduct experimental investigations and draw conclusions from them.
Assessment Information
Written Examination 70
Assessed Assignments 30
Oral Presentations 0

Two assignments, first on building belief networks, second on learning probabilistic models of data.

If delivered in semester 1, this course will have an option for semester 1 only visiting undergraduate students, providing assessment prior to the end of the calendar year.
Special Arrangements
Additional Information
Academic description Not entered
Syllabus *Introduction
* Probability
o events, discrete variables
o joint, conditional probability
* Discrete belief networks, inference
* Continuous distributions, graphical Gaussian models
* Learning: Maximum Likelihood parameter estimation
* Decision theory
* Hidden variable models
o mixture models and the EM algorithm
o factor analysis
o ICA, non-linear factor analysis
* Dynamic hidden variable models
o Hidden Markov models
o Kalman filters (and extensions)
* Undirected graphical models
o Markov Random Fields
o Boltzmann machines
* Information theory
o entropy, mutual information
o source coding, Kullback-Leibler divergence
* Bayesian methods for
o Inference on parameters
o Model comparison

Relevant QAA Computing Curriculum Sections: Artificial Intelligence
Transferable skills Not entered
Reading list * The course text is "Pattern Recognition and Machine Learning" by C. M. Bishop (Springer, 2006).
* In addition, David MacKay's book "Information Theory, Inference and Learning Algorithms" (CUP, 2003) is highly recommended.
Study Abroad Not entered
Study Pattern Lectures 20
Tutorials 8
Timetabled Laboratories 0
Non-timetabled assessed assignments 36
Private Study/Other 36
Total 100
KeywordsNot entered
Course organiserDr Michael Rovatsos
Tel: (0131 6)51 3263
Course secretaryMiss Kate Weston
Tel: (0131 6)50 2701
Help & Information
Search DPTs and Courses
Degree Programmes
Browse DPTs
Humanities and Social Science
Science and Engineering
Medicine and Veterinary Medicine
Other Information
Important Information
© Copyright 2011 The University of Edinburgh - 16 January 2012 6:17 am