University of Cambridge > Talks.cam > Signal Processing and Communications Lab Seminars > Rao-Blackwellized Particle Smoothing for Conditionally Linear Gaussian Models (NOTICE CHANGED TIME!)

Rao-Blackwellized Particle Smoothing for Conditionally Linear Gaussian Models (NOTICE CHANGED TIME!)

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Rachel Fogg.

Although Monte Carlo based particle filters and smoothers can be used for approximate inference in almost any kind of probabilistic state space models, the required number of samples for a sufficient accuracy can be high. The efficiency of sampling can be improved by Rao-Blackwellization, where part of the state is marginalized out in closed form, and only the remaining part is sampled. Because the sampled space has a lower dimension, fewer particles are required. In this talk I will discuss on Rao-Blackwellization in the context of conditionally linear Gaussian models, and present efficient Rao-Blackwellized versions of previously proposed particle smoothers.

This talk is part of the Signal Processing and Communications Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity