BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230228T015646Z
UID:58B39B32-7587-4846-98BA-4E842158E917
DTSTART;TZID=America/New_York:20230227T183000
DTEND;TZID=America/New_York:20230227T203000
DESCRIPTION:Cognitive EW: Assuring In-Mission Learning for EW\n\nThis prese
 ntation will discuss the challenges for assuring the performance of a syst
 em that can learn from novel experiences in the field. EW systems operate 
 at a timescale that means they cannot afford to learn post-mission\, or wi
 th human supervision. EW systems must learn from a single observation\, us
 ing self-supervised reinforcement feedback. The validation infrastructure 
 must therefore support automated closed-loop\, multi-resolution testing\, 
 and ways to test the effectiveness of actions. We must validate the learni
 ng process\, rather than validating the learned model.\n\nSpeaker(s): Dr. 
 Karen Haigh\, \n\nAgenda: \n630 - 700PM ARRIVAL\, REFRESHMENT & DINNER\n\n
 700 - 800PM EW PRESENTATION\n\n800 - 830PM Q&A\n\nRoom: Usual Meeting Area
 \, Bldg: Moose Lodge #1406\, 157 Dayton Blvd \, Melbourne\, Florida\, Unit
 ed States\, 32904
LOCATION:Room: Usual Meeting Area\, Bldg: Moose Lodge #1406\, 157 Dayton Bl
 vd \, Melbourne\, Florida\, United States\, 32904
ORGANIZER:bob.beck@ieee.org
SEQUENCE:11
SUMMARY:Cognitive Electronic Warfare: Assuring in-mission learning for EW b
 y Karen Haigh
URL;VALUE=URI:https://events.vtools.ieee.org/m/343757
X-ALT-DESC:Description: <br /><p>Cognitive EW: Assuring In-Mission Learning
  for EW</p>\n<p>This presentation will discuss the challenges for assuring
  the performance of a system that can learn from novel experiences in the 
 field. EW systems operate at a timescale that means they cannot afford to 
 learn post-mission\, or with human supervision. EW systems must learn from
  a single observation\, using self-supervised reinforcement feedback. The 
 validation infrastructure must therefore support automated closed-loop\, m
 ulti-resolution testing\, and ways to test the effectiveness of actions. W
 e must validate the learning process\, rather than validating the learned 
 model.</p><br /><br />Agenda: <br /><p>630 - 700PM&nbsp\; &nbsp\;ARRIVAL\,
  REFRESHMENT &amp\; DINNER</p>\n<p>700 - 800PM&nbsp\; &nbsp\;EW PRESENTATI
 ON</p>\n<p>800 - 830PM&nbsp\; &nbsp\;Q&amp\;A</p>
END:VEVENT
END:VCALENDAR