VS298: Natural Scene Statistics

From RedwoodCenter
Revision as of 23:50, 28 January 2014 by Bruno (talk | contribs)
Jump to navigationJump to search

This seminar will examine what is known about the statistical structure of natural visual and auditory scenes, and theories of how sensory coding strategies have been adapted to this structure. Topics include:

  • Theories of efficient and robust coding
  • ICA and sparse coding
  • Energy-based models: 'Product of experts' and 'Fields of experts'
  • Learning invariant representations through ‘slow feature analysis’
  • Manifold and Lie group models
  • Hierarchical models and ‘deep networks’


Instructor: Bruno Olshausen

Enrollment information:

VS 298 (section 4), 2 units
CCN: 66489

Meeting time and place:

Monday 6-8, Evans 560


Schedule:

Date Topic/Reading Presenter
Feb. 3 Barlow: Theory of redundancy reduction paper

Atick: Theory of whitening paper
Field: 1/f2 power spectrum and sparse coding paper

Anthony DiFranco

Dylan Paiton
Michael Levy

Feb. 10
Feb. 17 ** Holiday **
Feb. 24
March 3
March 10
March 17
March 24
March 31 ** Spring recess **
April 7
April 14
April 21
April 28
May 5
May 12