BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Bayesian Treatment for Uncertainty -- and its application in hea
 lth care  - Dr Cheng Zhang
DTSTART:20170926T140000Z
DTEND:20170926T150000Z
UID:TALK83641@talks.cam.ac.uk
CONTACT:Pat Wilson
DESCRIPTION:Machine learning has enabled and improved many real-life appli
 cations. However\,  when humans interact with machines an estimate of mode
 l uncertainty  is required\, especially in applications such as health car
 e. My research focuses on designing probabilistic models and advancing var
 iational inference for this kind of domain.\n\nIn this talk\, I will mainl
 y focus on two parts of my work. Firstly\, I will present probabilistic la
 tent variable models and their applications in health care.  I investigate
  the question of diagnostic prediction from various sources as a multi-vie
 w learning problem setting. I design a general framework consisting of a f
 actorized multi-view topic model for image annotation and diagnostic predi
 ction.\n\nSecondly\, I present my recent work on accelerating stochastic a
 pproximate inference.  We employ determinantal point processes for varianc
 e reduction and data re-balancing in stochastic gradient methods. Moreover
 \, we propose a unified view of black-box variational inference and import
 ance sampling\, and further introduce perturbative variational inference t
 hat can have a mass covering effect but at the same time maintain a low va
 riance.\n\nIn the end\, I conclude the talk with possible future work in t
 erms of both machine learning theory and its application to  health care. 
 \n\nSpeaker Bio:\nCheng Zhang is a postdoctoral research associate in the 
 machine learning group at Disney Research Pittsburgh.  She has received he
 r Ph.D. at the Department of Robotics\, Perception and Learning (RPL/ form
 er CVAP)\, School of Computer Science and Communication\, KTH Royal Instit
 ute of Technology\, Sep\, 2016.  Her thesis was on Structured Representati
 on Using Latent Variable Models. She has been a postdoctoral researcher in
  the same group till the end of 2016. She obtained her master's degree in 
 System Control and Robotics from KTH in fall 2011. During her PhD studies\
 , she visited Prof. Neil Lawrence’ group at the University of Sheffield 
 in 2013 and was an intern at Microsoft Research Cambridge in the Infer.Net
  group in summer 2014. She has received two grants from Stiftelsen Promobi
 lia (a Swedish research foundation) for research on robust inference for c
 omputer vision tasks where she is the PI. Her joint project with Karolinsk
 a Institutet (KI) on patient-centered decision support is funded by a Vinn
 ova (Sweden’s Innovation Agency) UDI step 1 grant. She is active in the 
 areas of machine learning and computer vision\, and with a strong interest
  in machine learning in health care.
LOCATION:CBL Seminar Room
END:VEVENT
END:VCALENDAR