[Lisa_seminaires] [teatalk-orgs] [Tea Talk] Dhruva Raman (Cambridge) Fri 19 April 2019 10h30 Mila Auditorium

saikrishna gottipati saikrishnagv1996 at gmail.com
Lun 15 Avr 10:08:18 EDT 2019


This week we have *Dhruva Raman* from *Univ of Cambridge *giving a
talk on  *Fundamental
Bounds on Learning Performance in Neural Circuits *at *10h30* on *19th
April* in *Mila Auditorium*.

If you are interested in* meeting Dhruva*, please book a slot in this google
sheet
<https://docs.google.com/spreadsheets/d/13k6e1rCDM1tD__MvxS-UDHMS9L6XsWcTvqs_atbmNRY/edit?usp=sharing>

See you there!
The Tea Talk Team

*TITLE*  Fundamental Bounds on Learning Performance in Neural Circuits

*ABSTRACT*
Biological neural circuits learn in spite of imperfect information on task
performance and noisy biological components. How can these problems be
mitigated? We use optimization theory to show how adding apparently
redundant neurons and connections to a network can improve learning
performance in the face of imperfect learning rules and corrupted error
signals. The theory shows how large neural circuits can exploit additional
connectivity to achieve faster and more precise learning. However, there is
a limit to the benefit of adding connections. Biologically, synapses
(connections strengths) are intrinsically unreliable. We show that
excessive network size eventually outcompetes the benefits to learning
performance. Consequently, there is an optimal size of network for a given
task, which we can calculate in specific cases.

*BIO*
Dhruva did his undergraduate (MMath) at the University of Warwick
(2008-2012), spent a year at the systems biology doctoral training centre
at the University of Oxford (2012-2013), and did his PhD in the Control
Group at the University of Oxford under the supervision of Antonis
Papachristodoulou (2013-2016). Since 2017 he has been a postdoc in the
control group at the University of Cambridge under the supervision of
Timothy O’Leary.
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: <http://mailman.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20190415/58911087/attachment-0001.html>


Plus d'informations sur la liste de diffusion Lisa_seminaires