BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computational Neuroscience Journal Club - Richard Turner (Universi
 ty of Cambridge)
DTSTART:20100223T160000Z
DTEND:20100223T170000Z
UID:TALK23108@talks.cam.ac.uk
CONTACT:Dr Jean-Pascal Pfister
DESCRIPTION:Statistical modeling of photographic images E P Simoncelli\, H
 andbook of Image and Video Processing\,pages 431--441. Academic Press\, Ma
 y 2005.\n\n\nOver the last 15 years it has been increasingly popular to mo
 del the visual cortex as performing inference in a latent variable model f
 or image statistics. The basic idea is that visual scenes consist of struc
 tural primatives\, like local edges at particular orientations and scales.
  In any one image only a relatively small number of these primitives are a
 ssumed to be present\, and so these models employ sparse latent variables 
 that describe the probability of occurrence. Cortex is then modelled as re
 presenting the posterior distribution over these latent variables\, given 
 the retinal image.\n\nIn this journal club\, I will review this modelling 
 work\, starting with independent component analysis\, and sparse coding\, 
 which have been used to model simple cells. I will then describe their gen
 eralisation to Gaussian Scale Mixtures\, which have been used to model bot
 h simple and complex cells. Finally I hope to describe the most recent wor
 k on these models by both Mike Lewicki and Eero Simoncelli. One of the mai
 n aims will be to assess this modelling work whilst wearing a machine lear
 ning hat.
LOCATION:Cambridge University Engineering Department\, Oatley Seminar Room
  2
END:VEVENT
END:VCALENDAR