Program

The summer school will feature lectures, practical courses, student talks, and an interesting series of evening talks.

Lectures will mainly focus on introducing a particular field, possibly followed by a limited amount of more advanced material emphasising the lecturer's recent work. They will take place over 4-6 sessions of 45 minutes each.
Practical courses are intended as "interactive lectures" in which students will obtain hands-on experience of the techniques involved. Each course will be given for around 20-30 students, and will last 2-3 hours.
One afternoon will be reserved for the students to present their work to the other attendees, either through posters or short talks. We hope to see many interesting problems in current machine learning research.
During evening talks, selected speakers from fields outside of machine learning will present overviews of their research, and describe interesting problems from which future collaborations might arise.

A preliminary schedule can be found here.

Lecture courses

Andrew Blake	Microsoft Research Cambridge	Topics in image and video processing
Olivier Bousquet	Google	Statistical learning theory
Nicolò Cesa-Bianchi	University of Milano	Online Learning
Arnaud Doucet	University of British Columbia	Sequential Monte Carlo methods
Zoubin Ghahramani	University of Cambridge	Graphical models
László Györfi	Budapest University	Machine learning and finance
Kenji Fukumizu	Institute of Statistical Mathematics Tokyo	Kernel Methods for Dependence and Causality
Carl E. Rasmussen	MPI / University of Cambridge	Bayesian inference and Gaussian processes
Gunnar Rätsch	Friedrich Miescher Laboratory	Machine Learning in Bioinformatics
Bernhard Schölkopf	MPI	Introduction to kernel methods
Alexander J. Smola	NICTA	Introduction to kernel methods
Lieven Vandenberghe	UC Los Angeles	Convex Optimisation

Joaquin Quinonero Candela	Microsoft Research Cambridge	Gaussian Processes
Manuel Davy	LAGIS	Practical sampling
Matthias Hein	Saarland University	Spectral Clustering and other graph based algorithms
Ulrike von Luxburg	MPI	Spectral Clustering and other graph based algorithms
Matthias Seeger	MPI	Variational Bayesian Inference
Yee Whye Teh	Gatsby Unit	Dirichlet Processes

Andreas Dengel	DFKI	Learning Mental Associations as a means to build Organizational Memories
Uwe D. Hanebeck	University of Karlsruhe	Stochastic Information Processing in Sensor Networks: Challenges, Some Solutions, and Open Problems
Oliver Kohlbacher	University of Tübingen	Lost in Translation -- Solving biological problems with machine learning
Joachim Weickert	Saarland University	Regularisation in Image Analysis