BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Latent Force Models with Gaussian Processes - Dr Neil Lawrence (Un
 iversity of Manchester)
DTSTART:20100301T110000Z
DTEND:20100301T120000Z
UID:TALK23146@talks.cam.ac.uk
CONTACT:Carl Scheffler
DESCRIPTION:Physics based approaches to data modeling involve constructing
  an accurate mechanistic model of data\,  often based on differential equa
 tions. Machine learning approaches are typically data driven---perhaps thr
 ough regularized function approximation.\n\nThese two approaches to data m
 odeling are often seen\nas polar opposites\, but in reality they are two d
 ifferent ends to a spectrum of approaches we might take.\n\nIn this talk w
 e introduce latent force models. Latent force models are a new approach to
  data representation that model data through unknown forcing functions tha
 t drive differential equation models.  By treating the unknown forcing fun
 ctions with Gaussian process priors we can create probabilistic models tha
 t exhibit particular physical characteristics of interest\, for example\, 
 in dynamical systems resonance and inertia. This allows us to perform a sy
 nthesis of the data driven and physical modeling paradigms. We will show a
 pplications of these models in systems biology and modelling of human moti
 on capture data.
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR