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:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69c233d8e8447
DTSTART;TZID=America/Toronto:20181214T150000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20181214T150000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/phd-seminar-p
 rogressive-memory-banks-incremental-domain
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 2306C Waterloo ON N2L 3G1 Canada
SUMMARY:PhD Seminar: Progressive Memory Banks for Incremental Domain\nAdapt
 ation
CLASS:PUBLIC
DESCRIPTION:NABIHA ASGHAR\, PHD CANDIDATE\n_David R. Cheriton School of Com
 puter Science_\n\nWe address the problem of incremental domain adaptation 
 (IDA). We\nassume each domain comes one after another\, and that we could 
 only\naccess data in the current domain. The goal of IDA is to build a\nu
 nified model performing well on all the domains that we have\nencountered.
  We propose to augment a recurrent neural network (RNN)\nwith a directly p
 arameterized memory bank\, which is retrieved by an\nattention mechanism a
 t each step of RNN transition. The memory bank\nprovides a natural way of 
 IDA: when adapting our model to a new\ndomain\, we progressively add new s
 lots to the memory bank\, which\nincreases the number of parameters\, and 
 thus the model capacity. 
DTSTAMP:20260324T064856Z
END:VEVENT
END:VCALENDAR