MBI Course on Statistical Learning

Spring 2014

(The class meets on selected Tuesdays  9:10am-11:15am in the MBI lecture room in Jennings hall)

The course covers basic concepts of modern statistical learning theory.  The theory itself is born out of the  challenge of understanding vast amounts of data routinely collected in modern science  and has led to the development of new tools in the field of statistics, as well as  has spawned new computer-assisted areas of  research,  such as data mining, machine learning, and bioinformatics. Many of these tools    have common underpinnings but are often described with different terminology. This course  attempts  to collect  some  main   ideas of statistical learning  into a common conceptual framework appropriate for  the audience with mathematical background.

Jan 21
Introduction and overview
ELS2 Chap 1,2
Jan 28
Computational methods for regression
ELS2 Chap 3
Feb 4
Linear and kernel-based classification
ELS2 Chap 4,6
Feb 18
Model assessment and selection ELS2 Chap 7
Feb 25
Mar 4
Tree based models and neural nets
ELS2 Chap 9, 11
Data set discussion
Mar 25
Random forests and ensemble learning ELS2 Chap 16
Apr 1
High dimensional data ELS2 Chap 18

ELS2- Elements of  Statistical Learning, Second Edition by T. Hastie  R. Tibshirani, and J. H. Friedman

Additional text with R code examples
An Introduction to Statistical Learning with Applications in R, by James Witten, Hasite, and Tibshirani
Green Buckeye Certified CEPH CAHME NIH NSF