Advanced Machine Learning2016HT
|
|
Course plan
No of lectures
Still to be decided, but approximately 5-10 lectures and 3-4 computer labs.
Recommended for
PhD students in Statistics, Computer Science, Applied Mathematics, and related engineering sciences.
The course was last given
Never before.
Goals
Learning about some commonly used probabilistic machine learning models, such as Bayesian networks, State-space models, and hidden Markov models.
Prerequisites
- Introduction to Machine Learning, 6 hp, or equivalent. It is ok to take this
course simultaneously with the Advanced course.
- Bayesian Learning, 6 hp, or equivalent.
- Some knowledge of MCMC methods (similar to what is included in the course
Bayesian learning).
Organization
Lectures and computer labs.
Contents
Bayesian networks, State space models, Hidden Markov models.
Literature
Pattern recognition and machine learning by C.M. Bishop, ISBN 9780387310732.
Lecturers
Mattias Villani, Oleg Sysoev and José Pena.
Examiner
Mattias Villani/José Pena
Examination
Lab reports
Credit
6 hp
Comments
This course is also given at the master's programme Statistics and Machine Learning and at the Machine learning and AI profile on the civil engineering programme in Software engineering.
Page responsible: Director of Graduate Studies