Workshop on Mathematics of Deep Learning 2017

Deep Learning has evolved into one of the hot topics in industry and science with a wide range of applications related to the processing and interpretation of large amounts of data. This includes recommendation and chat systems, image and language recongnition, classification, identification, knowledge discovery, simulation of complex physical phenomena, autonomous systems, and many other areas. While the success and progress of recent neural network architectures has been breathtaking, the mathematical understanding and analysis of these networks is still in its infancy.

However, a better understanding of the underlying structures would allow for the development of more efficient algorithms and shed light on the expressive power of architectures. Moreover, this also is a major issue for the application of deep learning methods in safety critical industrial areas such as autonomous driving.

The aim of the workshop is to bring together leading researches from institutes and industry with a focus on the mathematical analysis and interpretation of current learning approaches and related mathematical and technical fields, e.g. high-dimensional approximation, tensor methods, UQ, probabilistic optimization.

The workshop is jointly organized by the TU Berlin and WIAS with kind support of ECMath/MATHEON.

Invited Speakers

  • Afonso Bandeira (New York University)
  • Andrzej Cichocki (RIKEN Japan)
  • Nadav Cohen (HU Jerusalem)
  • Philipp Grohs (U Vienna)
  • Gerard Kerkyacharian (UPMC)
  • Stephane Mallat (ENS Paris)
  • Anthony Nouy (EC Nantes)
  • Ivan Oseledets (Skolkovo Institute)
  • Sergei Pereverzyev (RICAM)
  • Dominique Picard (U Paris Diderot)
  • Thomas Wiatowski (ETH Zürich)


Contact and further information

Phone: +49 30 20372-555