Data Mining and Statistical Learning DF21200, 2013HT Status Archive School Computer and Information Science (CIS) Division STIMA Owner Patrik Waldmann Homepage www.ida.liu.se/~732A33

Log in

---

Course plan

No of lectures

14x2 hours + 12 computer labs

Recommended for

Ph.D. students interested in data mining and related topics

The course was last given

Autumn 2009

Goals

Provide insight into the statistical foundations of data mining and related techniques. Provide practical experience of data-driven methods for prediction and classification.

Prerequisites

A total of at least 1.5 years of full-time studies in mathematics, statistics and computer science. At least one basic course in statistics and computer science, respectively. Basic courses in calculus and linear algebra.

Organization

One lecture (2h) per week. Computer labs almost every week

Contents

Regression methods (ridge regression, partial least squares analysis)
Discriminant analysis
Smoothing techniques (kernel smoothing, splines)
Generalized additive models
Artificial neural networks

Literature

Hastie, T., Tibshirani, R., Friedman, J. The Elements of Statistical Learning. second edition, Springer-Verlag, 2009. ISBN:0-387-84857

Lecturers

Oleg Sysoev
Patrik Waldmann

Examiner

Oleg Sysoev

Examination

Individual reporting of computer labs

Credit

12 credits

Comments

Page responsible: Anne Moe