Safety and Security of Deep Learning
10 April 2021 09:00 till 11 April 2021 17:00 | Add to my calendar
We are glad to announce that the ICERM Hot Topics Workshop "Safety and Security of Deep Learning" will be offered online on April 10-11, 2021.
Deep learning is profoundly reshaping the research directions of entire scientific communities. Yet, despite their indisputable success, deep neural networks are known to be universally unstable. This phenomenon is now very well documented and yields non-human-like behaviour of neural networks in the cases where they replace humans, and unexpected and unreliable behaviour where they replace standard algorithms in the sciences. The many examples produced over the last years demonstrate the intricacy of this complex problem and the questions of safety and security of deep learning become crucial.
The goal of this workshop is to bring together experts from mathematics, computer science, and statistics in order to accelerate the exploration of breakthroughs and of emerging mathematical ideas in this area.
- Genevera Allen (Rice University)
- Emmanuel Candes (Stanford University)
- Rachel Cummings (Georgia Institute of Technology)
- Ronald DeVore (Texas A&M University)
- Gitta Kutyniok (TU Berlin)
- Aleksander Madry (MIT)
- Cynthia Rudin (Duke University)
For more information and how to apply: https://icerm.brown.edu/events/htw-21-ssdl/
This ICERM workshop is fully funded by a Simons Foundation Targeted Grant to Institutes.
The organizing committee:
- Ben Adcock (Simon Fraser University)
- Simone Brugiapaglia (Concordia University)
- Anders Hansen (University of Cambridge)
- Clayton Webster (University of Texas)