BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learned image reconstruction for large scale tomographic imaging -
  Professor Andreas Hauptmann
DTSTART:20190830T130000Z
DTEND:20190830T140000Z
UID:TALK129100@talks.cam.ac.uk
CONTACT:J.W.Stevens
DESCRIPTION:Recent advances in deep learning for tomographic reconstructio
 ns have shown great potential to create accurate high quality images with 
 a considerable speed-up compared to classical reconstruction methods. This
  is especially true for model-based learned (iterative) reconstruction sch
 emes. However\, applicability to large scale inverse problems is limited b
 y available memory for training and extensive training times. \nIn this ta
 lk I will discuss applicability of learned image reconstruction approaches
  to tomographic data. In particular we will discuss various imaging scenar
 ios and modalities\, suitable approaches to design a robust learning task\
 , as well as some solutions to obtain scalable learned image reconstructio
 n for large scale and high dimensional data. \n
LOCATION:MR11\, Centre for Mathematical Sciences\, Wilberforce Road\, Camb
 ridge
END:VEVENT
END:VCALENDAR