About

Pre-doc Summer School on Learning Systems
Monday, July 3 to Friday July 7, 2017
Zürich, Switzerland


One of the most prominent scientific challenges of our time is to cope with the complexity which arises in biology, medicine, engineering, economics, sociology and many other areas of high societal relevance. Learning systems are able to perceive large and complex information, and they can adjust and adapt their behavior to influences from their environment.

Natural as well as artificial learning systems are often influenced by highly unreliable, stochastic factors. Both the natural sciences and the engineering sciences with their complementary scientific methods of analysis and synthesis explore such learning systems by interacting with them, by modeling them, and by explicit construction or reconstruction.

The Pre-doc Summer School on Learning Systems aims at teaching a fundamental understanding of perception, learning and adaption in complex systems to master students and to attract them for potential future PhD studies in this field. Students in computer science and related fields get the opportunity to attend tutorial lectures and practicals on various topics related to Learning Systems. In particular, researchers from the Max Planck Institute for Intelligent Systems and ETH Zurich as well as some external lecturers will present fundamental and advanced topics in areas such as causal models, deep learning, learning theory, robotics & control and computer vision.

Main Speakers

Jeannette Bohg (Max Planck Institute for Intelligent Systems, Tübingen)
Andreas Geiger (Max Planck Institute for Intelligent Systems, Tübingen)
Thomas Hofmann (ETH Zürich)
Martin Jaggi (EPFL Lausanne)
Lubor Ladicky (ETH Zürich)
Pawan Kumar (University of Oxford)
Gerard Pons-Moll (Max Planck Institute for Intelligent Systems, Tübingen)
Ruth Urner (Max Planck Institute for Intelligent Systems, Tübingen)

Evening lectures

Aurelien Bellet (Inria Lille, France)
Joao Carreira (Google DeepMind, London, UK)
Krzysztof Dembczynski (Poznań University of Technology, Poland)
Chris Russell (University of Edinburgh, UK)



Location (Map and Directions)

Eth zurich door
The Summer School will take place at
ETH Zurich
Department of Computer Science
CAB Building
Universitätstrasse 6
8092
Zurich

Map of relevant locations

Directions from Zurich main station to CAB building
Tram no. 6 (direction Zoo) from stop "Bahnhofstrasse/HB" or Tram no. 10 (direction Airport) from stop „Bahnhofplatz/HB“ to stop „ETH/UniversitätsSpital“.


Program

July 3rd (Monday)

Description From To
Thomas Hofmann: Natural Language Processing and Deep Learning 09:00 10:30
break/coffee 10:30 11:00
Gerard Pons-Moll: Virtual Humans 11:00 12:30
lunch 12:30 14:00
Workshop given by Thomas Hofmann
Workshop given by Gerard Pons-Moll
14:00 16:30
Krzysztof Dembczynski: Learning with large number of labels 17:00 18:30
Barbeque at CAB courtyard 19:00 ...

July 4th (Tuesday)

Description From To
Martin Jaggi: Optimization Algorithms for Machine Learning 09:00 10:30
break/coffee 10:30 11:00
Pawan Kumar: Frank-Wolfe Optimization for Dense CRFs and Piecewise Linear CNNs 11:00 12:30
lunch 12:30 14:00
Workshop given by Martin Jaggi
Workshop given by Pawan Kumar
14:00 16:30
Chris Russell: Nonrigid 3D reconstruction 17:00 18:30

July 5th (Wednesday)

Description From To
Martin Jaggi: Optimization Algorithms for Machine Learning (continuation) 09:00 10:30
break/coffee 10:30 11:00
Lubor Ladicky: Regression Forests for PDE 11:00 12:30
lunch 12:30 14:00
Workshop given by Martin Jaggi
Workshop given by Pawan Kumar
14:00 16:30
Aurelien Bellet: Learning Similarity and Distance Functions 17:00 18:30

July 6th (Thursday)

Description From To
Ruth Urner: Learning Theory 09:00 10:30
break/coffee 10:30 11:00
Andreas Geiger: Probabilistic Reconstruction 11:00 12:30
lunch 12:30 14:00
Workshop given by Ruth Urner
Workshop given by Andreas Geiger
14:00 16:30
Joao Carreira: Learning video representations from YouTube 17:00 18:30
Informal get-together, location to be announced 20:00 ...

July 7th (Friday)

Description From To
Ruth Urner: Learning Theory (continuation) 09:00 10:30
break/coffee 10:30 11:00
Jeannette Bohg: Robotics 11:00 12:30
lunch 12:30 14:00
Workshop given by Ruth Urner
Workshop given by Jeannette Bohg
14:00 16:30


Eligibility

The Pre-doc Summer School on Learning Systems is open to students who:

  • are enrolled in a Master’s program in computer science, computer engineering, or a closely related discipline (e.g. electrical engineering, mathematics, physics)
  • have finished their master’s degree not more than one year ago, i.e. not earlier than July 2016.

A maximum of 80 places are available.

Application

Deadline for application was April 30, 2017.

Application is closed now. Applicants will be informed by May 15, 2017 whether they are accepted.

Costs

  • There is no course fee for the summer school.
  • Meals are not included. Various options for inexpensive lunch are available in the near surroundings (e.g. ETH canteen, 10-15 CHF per meal) Coffee breaks and social events are included.
  • Students have to cover accommodation and travel costs themselves. For the expenses of different hostels see below.
  • A very limited number of scholarships (partially funding the accommodation and travel costs) are available. If you are in need of financial support to be able to attend the summer school, please contact Magdalena Seebauer.
  • If you are a student of a CLS member group, please indicate with the application (accommodation and travel costs will be covered for students of a CLS member group).

Social events

Details to be announced.


Accommodation

We have reserved a contingent of rooms in the following locations. Please indicate your interest in the registration form.

  • Hotel Ibis Zurich City West, Schiffbaustrasse 11, 8005 Zurich: twin and triple rooms (78 or 67 CHF per person per night, incl. breakfast)
  • Youth Hostel Zurich, Mutschellenstrasse 114, 8038 Zürich: beds in 4-bed and 6-bed rooms (43 or 41 CHF per person per night, incl. breakfast)
  • City Backpacker Hostel, Niederdorfstrasse 5, 8001 Zürich: beds in 6-bed rooms (37 CHF per person per night, excl. breakfast)

Further possibilities - to be booked individually:

Organizers

Thumb babbar

Rohit Babbar

MPI-IS, Empirical Inference

Thumb guney

Fatma Güney

MPI-IS, Autonomous Vision / Perceiving Systems
Thumb ladicky

Lubor Ladicky

ETH, Computer Vision and Geometry lab
Thumb seebauer

Magdalena Seebauer

ETH, Scientific Coordination

Contact

Magdalena Seebauer, Max Planck ETH Center for Learning Systems


FAQs

Do I need to be a citizen of a specific country to be eligible for application?
No, this program is open to students worldwide.

Will I get ECTS credits?
You will receive an attendance certificate at the end of the summer school which might enable you to get ECTS credits from your home university. No exam or grading will be provided.

What if I am available for a subset of the days? Can I attend partially?
Unfortunately no. Students are expected to commit for the entire duration.

Can I arrive already on Sunday evening?
Yes, we recommend to arrive on Sunday. We have reserved accommodation from Sunday, July 2 on (till Friday July 7).

Can I arrive even sooner than Sunday or stay longer than till Friday?
Sure, but you are responsible for the organization and payment of any extra nights. You may contact the hostel directly if you wish to extend your stay.

Do I need to bring a laptop?
Yes, you are expected to bring your own laptop. If this is a problem, please contact the organizers. Nevertheless, some of the workshops will be given in fully equipped computer labs.

What is the language used at the summer school?
All instruction and interaction will be in English.