About



Deep Learning: Theory and Practice
July 11-13, 2016, Donaueschingen, Germany

We are pleased to announce the First Max Planck ETH Workshop on Practical and Theoretical Aspects of Deep Learning. The workshop will take place on July 11-13, 2016 at the Wyndham Garden Hotel in Donaueschingen, Germany. We cordially invite all interested researchers from the Center for Learning Systems and fellow lab members, as well as Max Planck and ETH PhD students and post-docs to participate and actively contribute to this workshop.



Aims and Scope

Deep learning models have shown great promises in the past few years in many areas, including machine learning, natural language processing and computer vision. There has been much progress in this area in recent years, in terms of methods, applications as well as theoretical understanding. Many challenges remain: scalable models, faster learning, learning from smaller sample sets, and adoption to novel tasks. The workshop aims to bring together researchers to discuss recent advances and ongoing developments in deep learning as well as exchange their experience of current methods.

Key topics will include:

  • General discussion on current deep architectures as well as recent developments in deep learning. We would like participants to get up to speed with modern methods and understand the future research challenges.
  • Practical sessions: One aspect of the workshop is to help researchers become more familiar with various existing tools in deep learning (Tensorflow, Torch, Theano, caffe, etc). Support will be provided for researchers to use existing models on some fundamental problems in various areas such as in computer vision or natural language processing.
  • Theoretical understanding: Training deep learning models give rise to a non-convex optimization problem. While optimizing convex functions is fairly well understood, non-convex functions are much more challenging. We will review existing analyses and discuss how they give rise to practical insights to optimize such models.

Format

The workshop will include several research talks, a poster/demo sessions as well as practical sessions and reading groups.

We are excited to have the following invited speakers:



Submissions

All attendees are encouraged to present a poster or a demonstration of their current research.


Workshop location (Donaueschingen, Germany)

The workshop will take place at
Wyndham Garden Hotel
Hagelrainstrasse 17
78166 Donaueschingen
Germany
http://www.wyndham.com
More information about how to get to the location can be found here


Program

Schedule (talks) & poster sessions


Schedule (Preliminary)

July 11th (Monday)

Description From To
Arrival 11:00 12:00
Lunch 12:00 13:00
Welcome 13:00 13:30
Invited speaker 13:30 15:00
Contributing talks 15:00 16:00
Coffee break 16:00 16:30
Posters 16:30 18:00
Hike/walk 18:00 19:00
Dinner 19:30 ...

July 12th (Tuesday)

Description From To
Breakfast ... ...
Practical sessions 09:00 10:30
Coffee break 10:30 11:00
Practical sessions 11:00 12:30
Lunch 12:30 13:30
Invited speaker 13:30 15:00
Paper Discussions 15:00 16:00
Coffee break 16:00 16:30
Poster 16:30 18:00
Invited speaker 18:00 19:30
BBQ 19:30 ...
Activities 20:00 + ...

July 13th (Wednesday)

Description From To
Breakfast ... ...
Practical sessions 09:00 10:30
Coffee break 10:30 11:00
Practical sessions 11:00 12:30
Lunch 12:30 13:30
Paper discussions 13:30 14:30
Contributing talks 14:30 16:00
Departure 16:00 ...


Application


Event application period is now closed.
Confirmations of participation will be send out on June 8th, 2016

Organizers

Thumb lucchi

Aurélien Lucchi

Department of Computer Science, ETH Zurich, Switzerland
Thumb gehler

Peter Gehler

Max Planck Institute for Intelligent Systems, Tübingen, Germany
Thumb hofmann

Thomas Hofmann

Department of Computer Science, ETH Zurich, Switzerland