BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241109T143107Z
UID:B49D25FA-07E6-4A9D-8927-26C851312BBD
DTSTART;TZID=America/Chicago:20241108T174500
DTEND;TZID=America/Chicago:20241108T190000
DESCRIPTION:This presentation will discuss the challenges for assuring the 
 performance of a system that can learn from novel experiences in the field
 . Electronic Warfare (EW) systems operate at a timescale that means they c
 annot afford to learn post-mission\, or with human supervision. EW systems
  must learn from a single observation\, using self-supervised reinforcemen
 t feedback. The validation infrastructure must therefore support automated
  closed-loop\, multi-resolution testing\, and ways to test the effectivene
 ss of actions. We must validate the learning process\, rather than validat
 ing the learned model.\n\nSpeaker(s): Karen Haigh\n\nAgenda: \n5:45 - Netw
 orking and pizza\n\n6:00 - Administrative and introduction of speaker\n\n6
 :05 - Presentation\n\n6:50 - Question/answer period\n\nRoom: 106\, Bldg: E
 ngineering Research Building\, 1500 Engineering Drive\, Madison\, Wisconsi
 n\, United States\, 53706
LOCATION:Room: 106\, Bldg: Engineering Research Building\, 1500 Engineering
  Drive\, Madison\, Wisconsin\, United States\, 53706
ORGANIZER:
SEQUENCE:2
SUMMARY:Cognitive EW: Assuring In-Mission Learning for EW
URL;VALUE=URI:https://events.vtools.ieee.org/m/442252
X-ALT-DESC:Description: <br /><p>This presentation will discuss the challen
 ges for assuring the performance of a system that can learn from novel exp
 eriences in the field. Electronic Warfare (EW) systems operate at a timesc
 ale that means they cannot afford to learn post-mission\, or with human su
 pervision. EW systems must learn from a single observation\, using self-su
 pervised reinforcement feedback. The validation infrastructure must theref
 ore support automated closed-loop\, multi-resolution testing\, and ways to
  test the effectiveness of actions. We must validate the learning process\
 , rather than validating the learned model.</p><br /><br />Agenda: <br /><
 p>5:45 - Networking and pizza</p>\n<p>6:00 - Administrative and introducti
 on of speaker</p>\n<p>6:05 - Presentation</p>\n<p>6:50 - Question/answer p
 eriod</p>
END:VEVENT
END:VCALENDAR