Teaching

The Elements of Statistical Learning II

Lecture 13 and a short summary are online.

General Outline:

The course is the second part of a two semester course on Statistical Learning. The first part (WS 2005/2006) concentrated on chapters 1-10 of the book The Elements of Statistical Learning, Springer 2001, this follow up course consists of two parts. The first part will continue with chapters 11-14 of the book. The second part will deal with methods of Statistical Learning applied to problems in Bioinformatics. There will be two hours of lecture per week and one hour of tutorial (V2/Ü1).

This course covers a subject that is relevant for computer scientists in general as well as for other scientists involved in data analysis and modeling. It is not limited to the field of computational biology.

Lecturer: Jörg Rahnenführer

Tutor: Laura Tolosi

Course language: English

Time and location:

Course:	Weekly, Wednesdays 11.15-13.00, Building 46, Room 533.
Tutorial:	Biweekly, Fridays 11-13, Building 46, Room 023.
Office hours:	On appointment.

Target Group and Prerequisites:

The lecture is targeted to advanced students in math, computer science and science students with mathematical background.
Prerequisites: Vordiplom in Mathematics or Computer Science or equivalent. Students should know linear algebra and have basic knowledge in statistics.

Literature:

Hastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer 2001. Readers of the course are encouraged to acquire this book.

Contents: Tentative course and tutorial schedule

Lecture	Date	Topic
Lecture 1	Fri April 21	Repetition - Overview - Outlook
Lecture 2	Fri April 28	Neural Networks (HTF chapter 11)
Lecture 3	Wed May 3	Support Vector Machines (HTF chapter 12)
Lecture 4	Wed May 10	Prototype Methods and Nearest-Neighbors (HTF chapter 13)
Lecture 5	Wed May 17	Unsupervised Learning I (HTF chapter 14)
Lecture 6	Wed May 24	Unsupervised Learning II (HTF chapter 14)
Lecture 7	Wed May 31	Kernel Methods (HTF chapter 6)
Lecture 8	Wed June 14	Normalization of Gene Expression Data
Lecture 9	Wed June 21	Classification of Gene Expression Data
Lecture 10	Wed June 28	Statistical Analysis with the Gene Ontology
Lecture 11	Wed July 5	Classification of Protein Structures
Lecture 12	Wed July 12	Learning with Mixtures of Trees
Lecture 13	Wed July 19	Analysis of ArrayCGH Data

Tutorial	Date	Topic	HW Assigned	HW Due
Tutorial 0	Fri April 21	Repetition (Lecture 1)	HW 1
Tutorial 1	Fri May 5	Model Assessment + Boosting	HW 2	HW 1
Tutorial 2	Fri May 19	Neural Networks + Support Vector Machines	HW 3	HW 2
Tutorial 3	Fri June 2	Nearest-Neighbors + Unsupervised Learning	HW 4	HW 3
Tutorial 4	Fri June 16	Kernel Methods	HW 5	HW 4
Tutorial 5	Fri June 30	Analysis of Expression Data	HW 6	HW 5
Tutorial 6	Fri July 14	Analysis with the Gene Ontology		HW 6

Embedding into the Curricula Computer Science and Bioinformatics

Both parts of this course fulfil the requirements for the curricula of computer science and bioinformatics as optional course with 6 resp. 4 credit points (Spezialvorlesung, 6 bzw. 4 Leistungspunkte).

Requirements for the course certificate:

50% of the homework points and final exam (most likely oral).