BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b22830530e8
DTSTART;TZID=America/Toronto:20190920T090000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20190920T090000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-computational-benefits-intrinsic
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 3317 Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: The Computational Benefits of\nIntr
 insic Plasticity in Neural Networks
CLASS:PUBLIC
DESCRIPTION:NOLAN SHAW\, MASTER’S CANDIDATE\n_David R. Cheriton School of
  Computer Science_\n\nIn this work\, I study the relationship between a lo
 cal\, intrinsic\nupdate mechanism and a synaptic\, error-based learning me
 chansim in\nANNs. I present a local intrinsic rule that I developed\, dubb
 ed IP\,\nthat was inspired by the Infomax rule. Like Infomax\, this IP rul
 e\nworks by controlling the gain and bias of a neuron to regulate its\nrat
 e of fire. I discuss the biological plausibility of this rule and\ncompare
  it to batch normalisation.
DTSTAMP:20260312T024256Z
END:VEVENT
END:VCALENDAR