BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:LCN Seminar: Efficient learning and generalization in networks wit
 h “material” synapses
DTSTART:20150122T133000
DTSTAMP:20260501T103515Z
UID:9dcf5594edbf50b53ef3e371565e7aba1ed5795c3187212b33b720a1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Riccardo ZECCHINA\nTheoretical Physics Department of Applied S
 cience and Technology\, Politecnico di Torino\nWe will discuss how the rec
 ent advances in statistical physics of random constraint satisfaction prob
 lems can contribute to learning problems in neural systems.\nSpecifically 
 we shall describe the main conceptual challenges related to learning with 
 discrete synapses (down to the binary case) and how some of these challeng
 es can be solved efficiently by message-passing algorithms.\nOn-going appl
 ications to “deep” networks\, hardware in situ learning\, efficient Ba
 yesian predictions and to input supervised learning in attractor networks 
 will be mentioned.
LOCATION:AAC120 http://plan.epfl.ch/?room=AAC120
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR