BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Laura WALLER: End-to-end Learning for Computational Microscopy
DTSTART:20210527T170000
DTEND:20210527T180000
DTSTAMP:20260511T081148Z
UID:cb9ccb8eb17336fc74c45962ed6038b06dfc91175cbf79b273539825
CATEGORIES:Conferences - Seminars
DESCRIPTION:Laura Waller\, UC Berkeley\, USA \nThis event is part of the 
 EPFL Seminar Series in Imaging (https://imagingseminars.org).\n\nAbstract.
  Computational imaging involves the joint design of imaging system hardwar
 e and software\, optimizing across the entire pipeline from acquisition to
  reconstruction. Computers can replace bulky and expensive optics by solvi
 ng computational inverse problems.\n\nThis talk will describe end-to-end l
 earning for development of new microscopes that use computational imaging 
 to enable 3D fluorescence and phase measurement. Traditional model-based i
 mage reconstruction algorithms are based on large-scale nonlinear non-conv
 ex optimization\; we combine these with unrolled neural networks to learn 
 both the image reconstruction algorithm and the optimized data capture str
 ategy.\n\nBiography. Laura Waller is the Ted Van Duzer Endowed Associate
  Professor at the University of California\, Berkeley. Her main interests
  lie in the development of computational imaging methods for phase imagin
 g\, super-resolution microscopy and lensless imaging. 
LOCATION:https://epfl.zoom.us/j/81189917524
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR