QLS seminar (Daniele Musso) via Zoom on 20 July 2021 at 15.00, CET

[Quantitative Life Sciences Section]

On Tuesday, 20 July at 15:00 CET, Dr Daniele Musso (Centro de 
Supercomputacion de Galicia (CESGA), Santiago de Compostela, Spain) will 
give a webinar titled:

*Local entropy, a selected topic in the physics of deep learning*

Abstract:
Insight and methods coming from physics have ever since helped to 
improve our understanding and design of neural networks. The 
interdisciplinary potential of techniques borrowed from statistical 
physics and information theory, such as entropic regularizations and 
renormalization, has not yet exhausted its drive in machine learning. 
After a non-technical description of such a panorama, the talk delves 
into a specific line of research based on local entropy. Local entropy 
represents a refinement of standard entropy and defines a 
coarse-graining technique helpful in understanding and improving deep 
neural networks. It allows for further refinement, entailing anisotropy 
in synaptic space and time dependence. As such, it offers a versatile 
framework where to study architecture-aware regularization procedures. 
Besides, a scheduling protocol where the regularization is strong in the 
early-stage of the training and then fades progressively away 
constitutes an alternative to standard initialization procedures. We 
conclude with some future perspectives, mainly related 
tospontaneously/explicitly broken scale invariance and hints of 
spacetime geometry in deep networks.


Indico: http://indico.ictp.it/event/9687/

Zoom Meeting ID to attend the online seminar: 475-819-702

Join Zoom Meeting:https://zoom.us/j/475819702 <https://zoom.us/j/475819702>

/If you haven't registered for previous QLS webinars, please contact 
qls at ictp.it *by Friday, 16 July *to obtain the PASSWORD for this zoom 
meeting./

-- 
Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-2240623
www.ictp.it/research/qls.aspx
e-mail:qls at ictp.it



------------------------------

Subject: Digest Footer

_______________________________________________
Send science-ts mailing list submissions to
         science-ts at lists.ictp.it

To subscribe, unsubscribe or view the list archives via the World Wide Web,
visit https://lists.ictp.it/mailman/listinfo/science-ts
or, via email, send a message with subject or body 'help' to
         science-ts-request at lists.ictp.it

When replying, please edit your Subject line so it is more specific than
'Re: Contents of science-ts digest...'


------------------------------

End of science-ts Digest, Vol 17, Issue 212
*******************************************