[Back to course home page]

Special course in Information Science II (4 ov, L)

Spring 2004

Place: Seminar room T4 in T-building
Time: Thursdays 14 - 16, starting on January 22
Language: English
Credit points: 4
Lecturer: Prof Juha Karhunen
Assistant: M.Sc. Antti Honkela
Web page: http://www.cis.hut.fi/Opinnot/T-61.182/

Information Theory and Machine Learning

The course is based on selected parts of the book

David J.C. MacKay: Information Theory, Inference, and Learning Algorithms, Cambridge Univ. Press, 2003, xii+628 pages.

The book has been received rather enthusiastically. More information on it can be found on its home page http://www.inference.phy.cam.ac.uk/mackay/itila/.
There is also an electronic version of the book freely available in different formats.

The book deals in an unique way information theory, inference, and machine learning, which are often taught separately but are actually closely related. The topics lie at the heart of many areas of science and engineering, such as communication, signal processing, data mining, pattern recognition, machine learning, cryptography, and bioinformatics.

In this course, we shall deal with basic information theory and coding, as well as Bayesian inference methods and their connections. Some topics in neural networks complementing the neural network courses given in our laboratory will be discussed, too. Advanced topics in information theory and coding are skipped in this special course.

Practical arrangements

The course is arranged in the usual way in as a seminar. The first meeting will be on Thursday 22nd January at 14:15 in the lecture room T4 in the Computer Science Building at HUT. After this, the course continues weekly at the same time in the same place. The details of the course will be determined later on after the number of the participants is roughly known.

Prerequisites

The course is intended both for graduate students and undergraduate students who have already passed most of their studies towards the M.Sc. degree. Passing the course successfully requires a certain mathematical maturity and a basic knowledge of probability theory and linear algebra.

Requirements for passing the course

To pass the course with 4 credits, you have to at least

• Sufficient participation in the seminar meetings;
• Giving one's own talk(s);
• Solving a sufficient percentage (usually 50%) of the problems chosen from the book;
• Possibly performing some computer assignment(s).

Detailed requirements will be decided later on.

Contact information

The responsible teacher of the course is Prof. Juha Karhunen, email Juha.Karhunen@hut.fi, room TB327, tel. 451 3270. The course assistant is M.Sc. Antti Honkela, email: Antti.Honkela@hut.fi, room TB311.

Welcome!

Prof. Juha Karhunen