NTR Webinar: Modern Hopfield Networks in AI and Neurobiology

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 June 1 Dmitry Krotov, MIT-IBM Watson AI Lab, IBM Research, Cambridge, MA, USA, led a technical Zoom webinar on Modern Hopfield Networks in AI and Neurobiology. 

About the webinar: 

Modern Hopfield Networks or Dense Associative Memories are recurrent neural networks with fixed point attractor states. 

In contrast to conventional Hopfield Networks, their modern versions have a very large memory storage capacity, which makes them appealing tools for many problems in machine learning and cognitive and neuro-sciences. 

Mr. Krotov introduced an intuition and a mathematical formulation of this class of models, and gave examples of problems in AI that can be tackled using these new ideas. 

He also explained how different individual models of this class, e.g. attention mechanism in transformers, arise from their general mathematical formulation.

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Your email address will not be published.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 *