NTR Webinar: Ordinary Differential Equations in Nonordinary Neural Networks

NTR organizes and hosts technical webinars about neural networks and invites speakers from all over the world to lead them. Webinars are held on Tuesdays and most are in Russian. 

On April 6 Talgat Daulbaev, Skoltech and Alexandr Katrutsa, Skoltech, Moscow, Russia, led a technical Zoom webinar on Ordinary Differential Equations in Nonordinary Neural Networks.

About the webinar: 

The webinar focuses on so-called neural ODEs. 

Neural network architecture is based on ordinary differential equations that simulate the continuous dynamics of hidden state representations. Special attention was paid to the methods of effective training of such models. The work was published in the proceedings of NeurIPS 2020 conference. 

Also listed was the important applications of neural ODEs in machine learning problems. Finally, the open problems in the field were discussed.

Materials available:

Webinar recording (in Russian)

Webinar presentation (in English)

Moderator and contact:

NTR CEO Nick Mikhailovsky: nickm@ntrlab.com

Leave a Reply

Your email address will not be published. Required fields are marked *