BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20200922T023005Z
UID:998438DA-A6F1-4B9A-9458-F1009AFBD2E3
DTSTART;TZID=Etc/GMT-5:20201005T095500
DTEND;TZID=Etc/GMT-5:20201005T105500
DESCRIPTION:This talk addresses microwave imaging problems using physical-i
 nsight-assisted machine learning (ML). Solving wave imaging problems using
  ML has attracted researchers’ interests in recent years. However\, most
  existing works in this direction directly adopt ML as a black box. ML app
 roaches have not yet had the profound impact on scientific computation pro
 blems as they have had for object classification. In fact\, researchers ha
 ve gained\, over several decades\, much insightful domain knowledge on wav
 e physics and in addition some of these physical laws present well-known m
 athematical properties (even analytical formulas)\, which do not need to b
 e learnt by training with a lot of data. This talk demonstrates that it is
  of paramount importance to address the problem of how profitably combinin
 g ML with the available knowledge on underlying physics of electromagnetic
 s.\n\nSpeaker(s): Dr. Xudong Chen\, \n\nHouston\, Texas\, United States\, 
 Virtual: https://events.vtools.ieee.org/m/240638
LOCATION:Houston\, Texas\, United States\, Virtual: https://events.vtools.i
 eee.org/m/240638
ORGANIZER:christopher.b.sanderson@ieee.org
SEQUENCE:1
SUMMARY:Physical-Insight Assisted Machine Learning in Microwave Imaging
URL;VALUE=URI:https://events.vtools.ieee.org/m/240638
X-ALT-DESC:Description: <br /><p><span style="font-size: 12pt\;">This talk 
 addresses microwave imaging problems using physical-insight-assisted machi
 ne learning (ML).&nbsp\; Solving wave imaging problems using ML has attrac
 ted researchers&rsquo\; interests in recent years. However\, most existing
  works in this direction directly adopt ML as a black box. ML approaches h
 ave not yet had the profound impact on scientific computation problems as 
 they have had for object classification. In fact\, researchers have gained
 \, over several decades\, much insightful domain knowledge on wave physics
  and in addition some of these physical laws present well-known mathematic
 al properties (even analytical formulas)\, which do not need to be learnt 
 by training with a lot of data. This talk demonstrates that it is of param
 ount importance to address the problem of how profitably combining ML with
  the available knowledge on underlying physics of electromagnetics.</span>
 </p>
END:VEVENT
END:VCALENDAR