TILS8000 Elements of statistical learning (5 cr)
The course gives an overview of modern statistical methods for mathematically oriented students. The main focus is in prediction models and assessment of their performance in new data. The course starts with linear models and proceeds to additive generalized models and other non-linear models. Smoothing, splines and regularization play an important role. The methods are applied to real and simulated data.
Course exam, exercises and practical assignment
The grades are determined by the success in the course exam and possibly also by the performance shown in the exercises and the practical assignment.
- knows linear and non-linear methods for regression and classification
- knows approaches for model assessment and model selection
- knows approaches for regularization and smoothing
- knows some methods for unsupervised learning
- can carry-out data-analysis with real data
Description of prerequisites
Available at https://web.stanford.edu/~hastie/Papers/ESLII.pdf
- Hastie, T., Tibshirani, R. & Friedman, J. (2009). The Elements of Statistical Learning, Second Edition. Springer, Berlin.<br />Available at http://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf; ISBN: 978-0-387-84857-0
Teaching (5 cr)
Kurssitentti, harjoitustehtävät ja harjoitustyö