| TDDE07 |
Bayesian Learning, 6 ECTS credits.
/Bayesianska metoder/
For:
D
IT
U
|
| |
Prel. scheduled
hours: 48
Rec. self-study hours: 112
|
| |
Area of Education: Technology
Main field of studies: Computer Engineeing, Computer Science
|
| |
Advancement level
(G1, G2, A): A
|
|
Aim:
The course gives a solid introduction to Bayesian learning, with special emphasis on theory, models and methods used in machine learning applications. The student will learn about the basic ideas and concepts in Bayesian analysis from detailed analysis of simple probability models. The course presents simulation algorithms typically used in practical Bayesian work, and course participants will learn how to apply those algorithms to analyze complex machine learning models.
After completing the course the student should be able to:
- derive the posterior distribution for a number of basic probability models
- use simulation algorithms to perform a Bayesian analysis of more complex
models
- perform Bayesian prediction and decision making
- perform Bayesian model inference.
|
|
Prerequisites: (valid for students admitted to programmes within which the course is offered)
Mathematical analysis; Linear Algebra; Probability and Statistics; Machine Learning; Basic programming.
Note: Admission requirements for non-programme students usually also include admission requirements for the programme and threshhold requirements for progression within the programme, or corresponding.
|
|
Supplementary courses:
Advanced Machine Learning, Text Mining, Visual Object Recognition and Detection
|
|
Organisation:
The course consists of lectures, exercises, seminars and computer labs. The lectures introduce concepts and theories that students then use in problem solving at the exercises and computer labs. The seminars are used for student presentations of the computer lab reports and discussions.
|
|
Course contents:
Likelihood, Subjective probability, Bayes theorem, Prior and posterior distribution, Bayesian analysis of the following models: Bernoulli, Normal, Multinomial, Multivariate normal, Linear and nonlinear regression, Binary regression, Mixture models; Regularization priors, Classification, Naïve Bayes, Marginalization, Posterior approximation, Prediction, Decision theory, Markov Chain Monte Carlo, Gibbs sampling, Bayesian variable selection, Model selection, Model averaging.
|
|
Course literature:
Gelman, A., Carlin, J.B., Stern, H. S., Dunson, D. B., Vehtari, A., and Donald Rubin,
D.B., Bayesian Data Analysis, 3rd edition. Chapman & Hall, 2013.
|
|
Examination: |
|
Computer examination
Computer assignments
|
3 ECTS
3 ECTS
|
| |
|
DAT1 is an exam in a computer hall that tests students' theoretical knowledge and problem-solving skills in Bayesian learning.
UPG1 consists of computer exercises that tests the students' ability to translate theoretical knowledge into practical problem solving in Bayesian learning. |
Course language is English.
Department offering the course: IDA.
Director of Studies: Ann-Charlotte Hallberg
Examiner: Mattias Villani
Course Syllabus in Swedish
|
|