BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:225526
DTSTAMP:20251023T101359Z
DTSTART;TZID=America/New_York:20251031T110000
DTEND;TZID=America/New_York:20251031T115000
URL;TYPE=URI:https://wpiedudev.wpi.edu/news/calendar/events/department-math
 ematical-sciences-colloquium-george-yin-university-connecticut
SUMMARY:Department of Mathematical Sciences Colloquium: George Yin, Univers
 ity of Connecticut
DESCRIPTION:\n\n\n      \n\n\n\nDepartment of Mathematical Sciences\nColloq
 uium\nFriday, October 31st, 2025\n11:00AM-11:50AM\nStratton Hall 202\nSpea
 ker: George Yin, University of Connecticut\nTitle: Computational Nonlinear
  Filtering: A Deep Learning Approach\nAbstract:Nonlinear filtering is a fu
 ndamental problem in signal processing, information theory, communication,
  control and optimization, and systems theory. In the 1960s, celebrated re
 sults on nonlinear filtering such the Kushner equation and the Duncan-Mote
 nsen-Zakai equation were obtained.Nevertheless, the computational issues f
 or nonlinear filtering remained to be a long-standing and challenging prob
 lem. In this talk, in lieu of treating the stochastic partial differential
  equations for obtaining the conditional distribution or conditional measu
 re, we construct finite-dimensional approximations using deep neural netwo
 rks for the optimal weights. Two recursions are used in the algorithm. One
  of them is the approximation of the optimal weight and the other is for a
 pproximating the optimal learning rate. Convergence and rates of convergen
 ce will be discussed together with some examples.[This is a joint work wit
 h Hongjiang Qian (Auburn University) and Qing Zhang (University of Georgia
 ).]\n
END:VEVENT
END:VCALENDAR