I00056 (I00056)
Lerende en redenerende systemen*
< 2006/2007 > 05-02-2007 t/m 01-07-2007 () L
Informatica - Bachelor (2003) Gegevens: Informatie- en kennissystemen (6 ec) (6 ec)
Informatiekunde - Bachelor (2003) Subject van verandering en bestendiging (6 ec)
omvang
6 ec (168 uur) : 32 uur plenair college, 32 uur groepsgewijs college, 0 uur computerpracticum, 0 uur 'droog' practicum, 16 uur gesprekken met de docent, 32 uur onderling overleg met medestudenten (werkgroepen, projectwerk e.d.), 56 uur zelfstudie
investering
6 ec * 28 u/ec + #std * (1 + 6ec * 0.15 u/student/ec)
inzet tentatief

examinator
afdeling
tijdbesteding

prof. dr. Tom Heskes
das
145u.

speciale web-site
http://www.cs.ru.nl/~tomh/onderwijs/lrs

 

How can we construct systems that learn? Or more specifically: how can we extract relevant, interesting information from huge databases? Those are the questions that we will discuss within this course. You will learn that there are different algorithms, depending both on the questions that you ask and on properties of the data involved. You will implement algorithms and apply them to existing data sets.

Leerdoelen

  • What kind of problems can be solved with data mining / machine learning?
  • Which algorithms can be used to solve these problems?
  • How do I implement and apply these algorithms?
  • How do I evaluate the quality of the solution obtained?

Onderwerpen

Various tasks with corresponding algorithms: explorative data analysis (histograms, boxplots, principal component analysis, multi-dimensional scaling), descriptive modelling (clustering, probability models), classification (discriminant analysis, naive Bayes, decision trees, nearest neighbors), regression (linear, neural networks) Basic principles: distance measures, uncertainty, maximum likelihood estimation, Bayesiaanse theory, error functions, search and optimalization procedures, cross-validation

Werkvormen

  • Written exam
  • Exercises
  • Project

Tentaminering

Two written exames (closed book) and a course project.

Literatuur

  1. "Introduction to data mining", by Tan, Steinbach and Kumar
  2. "Data Mining: Introductory and Advanced Topics", by Dunham
  3. "Principles of data mining", by Hand, Mannila and Smyth
  4. "Data mining, concepts and techniques", by Han and Kamber


Evaluatie: studentenquêtes ; geen docentevaluatie bekend Rendement: 30 begonnen, 18 echt meegedaan, 7 geslaagd met 1e kans, 12 geslaagd totaal
Q: