NTR Webinar: Sleep, Memory and Artificial Intelligence

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 22 Maksim  Bazhenov, University of California, San Diego, USA, led a technical Zoom webinar on Sleep, Memory and Artificial Intelligence. 

About the webinar: 

Previously encoded memories can be damaged by the encoding of new memories, especially when they are relevant to new data and therefore can be disrupted by new training – a phenomenon called “catastrophic forgetting.”

Human and animal brains are capable of continual learning, allowing them to learn from past experience and to integrate newly acquired information with previously stored memories. A range of empirical data suggest the important role of sleep in consolidation of recent memories and protection of past knowledge from catastrophic forgetting. 

I started by describing the main features and mechanisms of sleep in the brain. Then I described some of our recent results on application sleep related ideas in computational models and artificial intelligence.

Materials:

https://ucsdnews.ucsd.edu/pressrelease/can-sleep-protect-us-from-forgetting-old-memories  (in English)

https://elifesciences.org/articles/51005  (in English)

https://arxiv.org/abs/1908.02240  (in English)

https://www.kommersant.ru/doc/4458729 (in Russian) 

Articles that were mentioned during the webinar: 

https://arxiv.org/abs/2106.11908  (in English) 

https://arxiv.org/abs/2106.08446  (in English)

https://arxiv.org/abs/2104.04132  (in English)

https://arxiv.org/abs/2103.04780  (in English)

https://arxiv.org/abs/2011.09526  (in English)

Webinar recording (in Russian)

Webinar presentation (in English) – coming soon

Moderator and contact: NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published.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