[Back to course home page]

Special course in Information Science II

Information Theory and Machine Learning, Spring 2004

Seminar program and timetable

Date Chapter(s) of the book Presenter Slides
22.1. Initial arrangements, first meeting J. Karhunen PDF
29.1. 1. Introduction to Information Theory J.-H. Schleimer PDF
5.2. 2. Probability, Entropy, and Inference J. Raitio PDF
12.2. No seminar!
19.2. 3. More about Inference J. Ahola PDF
26.2. 4. The Source Coding Theorem, and
5. Symbol Codes, and
6. Stream Codes (central results)
T. Raiko PDF
4.3. 8. Correlated Random Variables, and
9. Communication over a Noisy Channel
T. Hirvonen PDF
11.3. No seminar!
18.3. 20. Clustering,
21. Exact Inference, and
22. Maximum Likelihood and Clustering
A. Vyskubov
18.3. 24. Exact Marginalization,
27. Laplace's Method, and
28. Model Comparison and Occam's Razor
A. Klami PDF
25.3. 29. Monte Carlo Methods T. Ukkonen
1.4. 30. Efficient Monte Carlo Methods, and
32. Exact Monte Carlo Methods
M. Harva
15.4. 31. Ising Models, and
33. Variational methods
J. Peltonen
22.4. 38. Neural Networks,
40. Capacity of a Single Neuron, and
41. Learning as Inference
Z. Yang PDF
29.4. 44. Supervised Learning in Multilayer Networks, and 45. Gaussian Processes J. Salojärvi PDF

There is no seminar on 8th April due to the Easter holiday.

The seminar is based on the book D. MacKay, Information Theory, Inference, and Learning Algorithms, Cambridge Univ. Press, 2003.

This timetable is also available as a PDF file.

Thursday, 29-Apr-2004 16:21:20 EEST