Reminder: Invitation to the ICTP Webinar Colloquium by Prof. Stéphane Mallat on "Mathematical Mysteries of Deep Neural Networks" on Wednesday 25 November 2020 at 16:hrs CET

[ICTP Director]

Dear All,

You are most cordially invited to the ICTP Webinar Colloquium by Prof. 
Stéphane Mallat on "Mathematical Mysteries of Deep Neural Networks" on 
Wednesday 25 November 2020 at 16:hrs CET.

*Pre-registration* is required at the following url: 
https://zoom.us/webinar/register/WN_IFSyVfu2RDm_EIipvwFzBQ

After registering, you will receive a confirmation email containing 
information about joining the webinar.

The talk will be available on livestream via the ICTP website, and also 
on ICTP's YouTube channel.

*Biosketch: *Stéphane Mallat is an applied mathematician, Professor at 
the Collège de France on the chair of Data Sciences. He is a member of 
the French Academy of Sciences, the Academy of Technologies and a 
Foreign Member of the US National Academy of Engineering. He was 
Professor at the Courant Institute of NYU in New York for 10 years, then 
at Ecole Polytechnique and Ecole Normale Supérieure in Paris. He also 
was the co-founder and CEO of a semiconductor start-up company. Stéphane 
Mallat's research interests include machine learning, signal processing 
and harmonic analysis. He developed the multiresolution wavelet theory 
with applications to image processing and sparse representations. He now 
works on mathematical understanding of deep neural networks, and their 
applications.

*Abstract: * Deep neural networks obtain impressive results for image, 
sound and language recognition or to address complex problems in 
physics. They are partly responsible of the renewal of artificial 
intelligence. Yet, we do not understand why they can work so well and 
why they fail sometimes, which raises many problems of robustness and 
explainability. Recognizing or classifying data amounts to approximate 
phenomena which depend on a very large number of variables. The 
combinatorial explosion of possibilities makes it potentially impossible 
to solve. One can learn from data only if the problem is highly 
structured. Deep neural networks appear to take advantage of these 
unknown structures. Understanding this "architecture of complexity" 
involves many branches of mathematics and is related to open questions 
in physics. I will discuss some approaches and show applications.

The talk will be followed by a question/answer session.

For info, please check the following link: http://indico.ictp.it/event/9472/

We look forward to seeing you online!

With best regards,

Office of the Director, ICTP