VS298: Natural Scene Statistics: Difference between revisions

From RedwoodCenter
Jump to navigationJump to search
No edit summary
No edit summary
Line 47: Line 47:
| Feb. 24
| Feb. 24
|  '''Higher-order statistics and sparse coding''' <br />
|  '''Higher-order statistics and sparse coding''' <br />
* Barlow (1972): sparse coding <br />
* Barlow (1972): Sparse coding <br />
* Field (1994): What is the goal of sensory coding? <br />
* Field (1994): What is the goal of sensory coding? <br />
* Bell & Sejnowski (1996):  Independent components analysis.
* Bell & Sejnowski (1996):  Independent components analysis.
Line 55: Line 55:
|  '''ICA and sparse coding''' <br />
|  '''ICA and sparse coding''' <br />
* Bell & Sejnowski (1997): ICA of natural images <br/>
* Bell & Sejnowski (1997): ICA of natural images <br/>
* Olshausen & Field (1997):  sparse coding of natural images <br />
* Olshausen & Field (1997):  Sparse coding of natural images <br />
* van Hateren & Ruderman (1998), Olshausen (2003):  ICA/sparse coding of natural video
* van Hateren & Ruderman (1998), Olshausen (2003):  ICA/sparse coding of natural video
|  
|  
Line 79: Line 79:
| March 31
| March 31
|  '''Energy-based models''' <br />
|  '''Energy-based models''' <br />
* Osindero & Hinton<br />
* Hinton:  Restricted Boltzmann machine <br />
* Roth & Black
* Osindero & Hinton:  Product of Experts <br />
* Roth & Black:  Fields of experts
|  
|  
|-
|-
Line 87: Line 88:
* Foldiak/Wiskott: slow feature analysis <br />
* Foldiak/Wiskott: slow feature analysis <br />
* Hyvarinen:  'Bubbles' <br />
* Hyvarinen:  'Bubbles' <br />
* Berkes et al.
* Berkes et al.:  factorizing 'what' and 'where' from video
|  
|  
|-
|-
Line 96: Line 97:
| April 21
| April 21
| '''Hierarchical models''' <br />
| '''Hierarchical models''' <br />
* Shan & Cottrell:  stacked ICA
* Karklin & Lewicki (2003):  density components <br />
* Shan & Cottrell:  stacked ICA <br />
* Cadieu & Olshausen (2012):  learning intermediate representations of form and motion
|  
|  
|-
|-

Revision as of 07:30, 3 February 2014

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.

Instructor: Bruno Olshausen

Enrollment information:

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

Meeting time and place:

Monday 6-8, Evans 560

General reading:

  • Natural Image Statistics by Hyvarinen, Hurri & Hoyer
  • Geisler WS (2008) Visual perception and the statistical properties of natural scenes, Annual Review of Psychology paper

Schedule:

Date Topic/Reading Presenter
Feb. 3 Redundancy reduction, whitening, and power spectrum of natural images
  • Barlow (1961): Theory of redundancy reduction paper
  • Atick (1992): Theory of whitening paper
  • Field (1987): 1/f2 power spectrum and sparse coding paper

Anthony DiFranco
Dylan Paiton
Michael Levy

Feb. 10 Whitening in time and color; Robust coding
  • Dong & Atick (1995): spatiotemporal power spectrum of natural movies
  • Ruderman (1998): statistics of cone responses
  • Karklin & Simoncelli (2012): noisy population coding of natural images
Feb. 17 ** Holiday **
Feb. 24 Higher-order statistics and sparse coding
  • Barlow (1972): Sparse coding
  • Field (1994): What is the goal of sensory coding?
  • Bell & Sejnowski (1996): Independent components analysis.
March 3 ICA and sparse coding
  • Bell & Sejnowski (1997): ICA of natural images
  • Olshausen & Field (1997): Sparse coding of natural images
  • van Hateren & Ruderman (1998), Olshausen (2003): ICA/sparse coding of natural video
March 10 Statistics of natural sound and auditory coding
  • Clark & Voss: '1/f noise and music'
  • Smith & Lewicki: sparse coding of natural sound
  • Klein/Deweese: ICA/sparse coding of spectrograms
March 17 Higher-order group structure
  • Geisler: contour statistics
  • Hyvarinen: subspace ICA/topgraphic ICA
  • Lyu & Simoncelli: radial Gaussianization
March 24 ** Spring recess **
March 31 Energy-based models
  • Hinton: Restricted Boltzmann machine
  • Osindero & Hinton: Product of Experts
  • Roth & Black: Fields of experts
April 7 Learning invariances through 'slow feature analysis'
  • Foldiak/Wiskott: slow feature analysis
  • Hyvarinen: 'Bubbles'
  • Berkes et al.: factorizing 'what' and 'where' from video
April 14 Manifold and Lie group models
April 21 Hierarchical models
  • Karklin & Lewicki (2003): density components
  • Shan & Cottrell: stacked ICA
  • Cadieu & Olshausen (2012): learning intermediate representations of form and motion
April 28 Deep network models
May 5
May 12