BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Ruchi Guo (UC Irvine)
DTSTART:20220303T170000Z
DTEND:20220303T180000Z
DTSTAMP:20260423T035608Z
UID:Inverse/73
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Inverse/73/"
 >A Deep Direct Sampling Method for Electrical Impedance and Diffuse Optica
 l Tomography</a>\nby Ruchi Guo (UC Irvine) as part of International Zoom I
 nverse Problems Seminar\, UC Irvine\n\n\nAbstract\nElectrical impedance to
 mography (EIT) and Diffuse Optical Tomography (DOT) are promising techniqu
 es for non-invasive and radiation-free type of medical imaging. They all c
 an be considered as inverse boundary value problems to identify PDE coeffi
 cients. But a high-quality reconstruction is always challenging due to its
  severe ill-posedness. Based on the idea of direct sampling methods (DSMs)
 \, we present a framework to construct deep neural networks for solving th
 ese two problems. It is able to capture the underlying mathematical struct
 ure from background projection of boundary measurement to coefficient dist
 ribution. The resulting Deep DSM (DDSM) is easy for implementation and its
  offline-online decomposition inherits efficiency from the original DSM th
 at does not need any optimization process in reconstruction. Additionally\
 , it is capable of systematically incorporating multiple Cauchy data pairs
  to achieve high-quality reconstruction and is also highly robust to large
  noise.\n
LOCATION:https://researchseminars.org/talk/Inverse/73/
END:VEVENT
END:VCALENDAR