[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive] HUT - CIS /Opinnot/T-61.6010/s01/description.shtml

T-61.181 Special course in Information Science I (4 ov) (L)

ICA, Autumn 2001

This graduate course is based on the brand new book Independent Component Analysis (J. Wiley, 2001), written by A. Hyvärinen, J. Karhunen, and E. Oja from our laboratory. The central parts of the book will be covered by lectures given by Profs. J. Karhunen and E. Oja.

Place: Seminar room Y313 in the main building of HUT
Time: Mondays 14 - 16, starting on September 17
Language: English
Credit points: maximum 4
Lecturers: Profs. Juha Karhunen and Erkki Oja
Assistant: M.Sc. Antti Honkela
Web page: http://www.cis.hut.fi/Opinnot/T-61.181/

Independent Component Analysis (ICA)

ICA is one of the most exciting topics in the fields of neural computation, advanced statistics, and signal processing. The text-book as well as the lecture course will provide a comprehensive introduction to this new technique complete with the mathematical background needed to understand and utilize it. It offers a general overview of the basics of ICA, important solutions and algorithms, and in-depth coverage of new applications in vision research, brain imaging, telecommunications, and more.

Prerequisites

You need only the basic knowledge about probability and statistics, matrix algebra, and algorithms in order to follow the course. The first lectures will be used to cover the necessary background.

Requirements for passing the course

To pass the course with 4 credits, you have to

  1. participate actively (at least 70% of the lectures)
  2. solve a set of exercise problems in the book at a sufficient level (at least 50% of the maximum points)
  3. carry out 2 computer projects and write brief reports on the results.

To pass with distinction, you must solve 90 % of your exercise problems in a satisfactory way, and do excellent projects with high level reports to match.

However, there is a certain overlap between this course and some previous graduate courses on ICA and unsupervised learning. If you have passed the Special Course on unsupervised learning held last autumn by Hyvärinen and Girolami, or one of the earlier ICA courses, please contact the lecturers to agree on the credit points.

Signing up for the course

Please come to the first lecture on Monday, September 17.
Welcome.

Erkki Oja Juha Karhunen


http://www.cis.hut.fi/Opinnot/T-61.6010/s01/description.shtml
webmaster@mail.cis.hut.fi
Monday, 24-Sep-2001 15:56:19 EEST