Continuum Models and Optimisation for Deep Neural Networks (Cancelled) (21w5143)

Organizers

(University of Sheffield)

Gitta Kutyniok (LMU Munich)

Carola Schönlieb (University of Cambridge)

Description

The Banff International Research Station will host the "Continuum Models and Optimisation for Deep Neural Networks" workshop in Banff from January 10 to January 15, 2021.


Deep learning methods are on the rise in every part of the digital world - face recognition and self-driving cars are already reality, doctors and engineers work to gether on automatic evaluation of patients' X-Ray and MRI data.

But are we "sure'' about what these algorithms are doing? Can we trust their results?

Banff's new workshop on Continuum models and optimisation for deep neural networks brings together scientists to discuss the foundations of our digital revolution, and to investigate the reliability of their results. As often, mathematics is the fundamental tool to examine today's challenges. Mathematics structures knowledge and identifies the strengths and limitations of deep learning algorithms. A better understanding of the maths behind deep learning helps us to develop more efficient algorithms and to put safety critical industrial areas such as autonomous driving on a firm ground.

A special feature of this workshop is its feminity - it is organized by three women at different stages in their lifes and careers, and it is probably the first regular Banff workshop with a majority of female speakers.


The Banff International Research Station for Mathematical Innovation and Discovery (BIRS) is a collaborative Canada-US-Mexico venture that provides an environment for creative interaction as well as the exchange of ideas, knowledge, and methods within the Mathematical Sciences, with related disciplines and with industry. The research station is located at The Banff Centre in Alberta and is supported by Canada's Natural Science and Engineering Research Council (NSERC), the U.S. National Science Foundation (NSF), Alberta's Advanced Education and Technology, and Mexico's Consejo Nacional de Ciencia y Tecnología (CONACYT).