Laboratory of Computer and Information Science / Neural Networks Research Centre CIS Lab Helsinki University of Technology

Laboratory of Computer and Information Science > Teaching > T-61.5060

Näitä sivuja ei päivitetä enää. Ole hyvä ja katso tietojenkäsittelytieteen laitoksen WWW-sivuja: http://ics.tkk.fi/fi/studies/.

These pages are not any more updated. Please, see web pages of Department of Information and Computer Science (ICS): http://ics.tkk.fi/en/studies/.

Näitä sivuja ei päivitetä enää. Ole hyvä ja katso tietojenkäsittelytieteen laitoksen WWW-sivuja: http://ics.tkk.fi/fi/studies/.

These pages are not any more updated. Please, see web pages of Department of Information and Computer Science (ICS): http://ics.tkk.fi/en/studies/.

Näitä sivuja ei päivitetä enää. Ole hyvä ja katso tietojenkäsittelytieteen laitoksen WWW-sivuja: http://ics.tkk.fi/fi/studies/.

These pages are not any more updated. Please, see web pages of Department of Information and Computer Science (ICS): http://ics.tkk.fi/en/studies/.

T-61.5060 Algorithmic methods of data mining (5 cr) P

Autumn 2007

26 + 26 (2 + 2) I-II

Heikki Mannila, academy professor, PhD (lecturer in charge)
Kai Puolamäki, lecturing researcher, PhD
Niko Vuokko, post-graduate student, MSc

E-mail: t615060@james.hut.fi

Lectures: T2 Mondays at 10-12 (September 10 - December 10, 2007). (No lectures on October 1 and October 29.)

Exercises: T2 Thursdays at 16-18 (starting September 13) No exercises on November 29!

Passing the course: Examination and a practical work.

Required preliminary knowledge: T-106.1220 Data Structures and Algorithms, two years worth of mathematics.

Language: English, All course material will be in English.

Times of the examinations are reported in The examination schedule.

Lectures and exercises are held in TKK's Tietotalo (Konemiehentie 2, Otaniemi).

Course data sheet 2007 (pdf)

Material

Lecture slides are available.

Background material: The course is in part based on material from the book H. Mannila, H. Toivonen, "Knowledge discovery in databases: the search for frequent patterns" (PS, PDF) that is also printed and available for loaning in copy-taking purpose in the exercise shelf of the laboratory (Tietotalo, 3rd floor, behind the glass door and beside the notice board and B302). The course will contain also other subjects and everything mentioned above is not covered. The book D. Hand, H. Mannila, P. Smyth, "Principles of Data Mining", MIT Press 2001 provides additional background material.


Description

The course will go through general questions in data mining such as pattern finding from data, clustering and approximating probability distributions. The course concentrates especially in analyzing discrete data using algorithmic techniques.

Summary of the course contents:

  1. Introduction: what is knowledge discovery, types of tasks, etc.
  2. Counting and approximate counting
  3. Discovery of frequent patterns: association rules, frequent episodes
  4. Basic ideas of clustering, selected algorithmic themes in cluster analysis
  5. Dimension reduction: random projections and other methods
  6. Link analysis: basic ideas
  7. Significance testing
  8. Possibly also some other themes

The course will contain a moderately easy practical work of writing summaries of given articles.

You are at: CIS → T-61.5060 Algorithmic methods of data mining

Page maintained by t615060@james.hut.fi, last updated Tuesday, 19-Aug-2008 10:51:03 EEST