BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probabilistic models for time-series with different underlying dyn
 amics regimes with application to robot imitation learning - Silvia Chiapp
 a
DTSTART:20101101T100000Z
DTEND:20101101T110000Z
UID:TALK27744@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:In this talk I will describe several probabilistic models for 
 analysing time-series containing different underlying dynamics regimes\, a
 nd discuss approximation schemes for dealing with intractable inference. I
  will first present a Bayesian approach to switching and mixtures of linea
 r dynamical systems (LDS) for incorporating prior domain knowledge and enf
 orcing a sparse parametrisation. I will then introduce an extension of the
  switching LDS with regime-duration-distribution and time-warping modeling
  for extracting repeated occurrences of basic shapes. I will show how thes
 e models can be applied to robot imitation learning.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR