BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Sigma-Points\, Cubatures and Rao-Blackwellization in Recursive Bay
 esian Estimation - Simo Särkkä\, Department of Biomedical Engineering an
 d Computational Science Aalto University\, Finland
DTSTART:20110601T131500Z
DTEND:20110601T140000Z
UID:TALK31363@talks.cam.ac.uk
CONTACT:Rachel Fogg
DESCRIPTION:Although\, sequential Monte Carlo based particle filters and s
 moothers\, in principle\, provide the Bayesian solution to any dynamic est
 imation problem presentable in probabilistic state space form\, they are n
 ot flawless. In particular\, as the state dimension grows\, the required n
 umber of particles quickly becomes high. Furthermore\, plain particle filt
 ers and smoothers cannot be used for inferring static or slowly varying pa
 rameters. One way to overcome these problems is to resort to Gaussian appr
 oximations for the full state posteriors or parts of the posteriors. Sigma
 -point and numerical cubature integration based filters and smoothers are 
 a recently developed class of methods for robust computation of such Gauss
 ian approximations. Rao-Blackwellization refers to partial closed form mar
 ginalization\, which can be used for avoiding sampling of Gaussian or appr
 oximately Gaussian parts of the state state\, or for marginalizing the sta
 tic parameters of the model in closed form. In this talk I will discuss th
 e sigma-point\, numerical integration and Rao-Blackwellization based filte
 ring and smoothing methods\, and present applications of the methods.
LOCATION:LR11\, Engineering\, Department of
END:VEVENT
END:VCALENDAR