Email Print Share

Mathematical and Scientific Foundations of Deep Learning (SCALE MoDL)

March 5, 2021 1:00 PM  to 
March 5, 2021 2:00 PM
Eastern Standard Time (New York, UTC/GMT-05:00)

Save the Date

The management team for the NSF program Stimulating Collaborative Advances Leveraging Expertise in the Mathematical and Scientific Foundations of Deep Learning (SCALE MoDL) (NSF 21-561) will host a webinar to provide an overview of the program.

Deep learning has met with impressive empirical success that has fueled fundamental scientific discoveries and transformed numerous application domains of artificial intelligence. Our incomplete theoretical understanding of the field, however, impedes accessibility to deep learning technology by a wider range of participants. Confronting our incomplete understanding of the mechanisms underlying the success of deep learning should serve to overcome its limitations and expand its applicability.

The SCALE MoDL program will sponsor new research collaborations consisting of mathematicians, statisticians, electrical engineers, and computer scientists. Research activities should be focused on explicit topics involving some of the most challenging theoretical questions in the general area of Mathematical and Scientific Foundations of Deep Learning. Each collaboration should conduct training through research involvement of recent doctoral degree recipients, graduate students, and/or undergraduate students from across this multi-disciplinary spectrum.

A wide range of scientific themes on theoretical foundations of deep learning may be addressed in these proposals. Likely topics include but are not limited to geometric, topological, Bayesian, or game-theoretic formulations, to analysis approaches exploiting optimal transport theory, optimization theory, approximation theory, information theory, dynamical systems, partial differential equations, or mean field theory, to application-inspired viewpoints exploring efficient training with small data sets, adversarial learning, and closing the decision-action loop, not to mention foundational work on understanding success metrics, privacy safeguards, causal inference, and algorithmic fairness.

Registration and Access to the Webinar

Participants should register (and may do so in advance) at the web page

https://nsf.zoomgov.com/webinar/register/WN_N9X5842dQ3-B6CkNvYXMwA

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

For real-time captioning on March 5, 1-2 PM EST, please click on the link:

https://www.captionedtext.com/client/event.aspx?EventID=4719026&CustomerID=321

For help, contact Zoom Technical support at +1-833-966-6468 (+1-833-Zoom-Gov) or email support@zoom.us.

How to Submit Questions

Participants may submit questions in advance through the registration form or by sending e-mail to: modl@nsf.gov. There will also be an opportunity to submit questions anonymously through the Zoom webinar Q&A feature.

Meeting Type
Webcast

Contacts
Huixia Wang, email: huiwang@nsf.gov

NSF Related Organizations
NSF-Wide
Division of Mathematical Sciences

Related Programs
Stimulating Collaborative Advances Leveraging Expertise in the Mathematical and Scientific Foundations of Deep Learning