BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:The topology of neural networks and their activation patterns
DTSTART:20151120T141500
DTEND:20151120T153000
DTSTAMP:20260919T032412Z
UID:8555878d1e4db0a0ffa06ea40cd4f3a36ff091a40eef82f60ad31c59
CATEGORIES:Conferences - Seminars
DESCRIPTION:Paolo Masulli (UNIL)\nThe dynamical evolution of a network is 
 strongly associated with its pattern of internal connections\, but the lac
 k of periodic patterns in the vast majority of biological networks\, and i
 n recurrent neural networks in particular\, makes it difficult to understa
 nd this correlation from a theoretical and formal approach. We use algebra
 ic topology to encode the connectivity structure of a network and build in
 variants that give us information on the dynamical evolution of a network\
 , looking in particular at the example of recurrent boolean artificial neu
 ral networks\, in order to relate topology and activation patterns. Our fi
 nal goal is to shed light on the problem of how the more complex temporal 
 activation patterns that are observed in biological networks are related w
 ith their topology.
LOCATION:MA 10
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR