VS298: Natural Scene Statistics: Difference between revisions

From RedwoodCenter
Jump to navigationJump to search
No edit summary
No edit summary
Line 1: Line 1:
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:
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.  
* 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''': [mailto:baolshausen@berkeley.edu Bruno Olshausen]
'''Instructor''': [mailto:baolshausen@berkeley.edu Bruno Olshausen]
Line 40: Line 33:
| Feb. 10
| Feb. 10
|  '''Whitening in time and color; Robust coding''' <br />
|  '''Whitening in time and color; Robust coding''' <br />
Dong & Atick:  spatiotemporal power spectrum of natural movies <br />
* Dong & Atick:  spatiotemporal power spectrum of natural movies <br />
Ruderman:  statistics of cone responses <br />
* Ruderman:  statistics of cone responses <br />
Karklin & Simoncelli:  noisy population coding of natural images
* Karklin & Simoncelli:  noisy population coding of natural images
|
|
|-
|-
Line 51: Line 44:
| Feb. 24
| Feb. 24
|  '''ICA and sparse coding''' <br />
|  '''ICA and sparse coding''' <br />
 
* Barlow (1972) <br />
* Olshausen & Field (1997) <br />
* Bell & Sejnowski (1997)
|  
|  
|-
|-
| March 3
| March 3
|  '''Statistics of natural sound and auditory coding''' <br />
|  '''Statistics of natural sound and auditory coding''' <br />
 
* Clark & Voss: '1/f noise and music' <br />
* Smith & Lewicki: sparse coding of natural sound <br />
* Klein/Deweese:  ICA/sparse coding of spectrograms
|  
|  
|-
|-
| March 10
| March 10
|  '''Higher-order group structure''' <br />
|  '''Higher-order group structure''' <br />
 
* Geisler: contour statistics <br />
* Hyvarinen:  subspace ICA/topgraphic ICA <br />
* Lyu & Simoncelli: radial Gaussianization
|  
|  
|-
|-
| March 17
| March 17
|   
'''Energy-based models''' <br />
* Osindero & Hinton<br />
* Roth & Black
|  
|  
|-
|-
| March 24
| March 24
|   
'''Learning invariances through 'slow feature analysis'''' <br />
* Foldiak/Wiskott: slow feature analysis <br />
* Hyvarinen:  'Bubbles' <br />
* Berkes et al.
|  
|  
|-
|-
Line 77: Line 81:
|-
|-
| April 7
| April 7
|   
'''Manifold and Lie group models''' <br />
|  
|  
|-
|-
| April 14
| April 14
|   
| '''Hierarchical models''' <br />
* Shan & Cottrell: stacked ICA
|  
|  
|-
|-
| April 21
| April 21
|   
'''Deep network models''' <br />
|  
|  
|-
|-

Revision as of 01:30, 29 January 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


Schedule:

Date Topic/Reading Presenter
Feb. 3 Redundancy reduction, whitening, and power spectrum of natural images
  • 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 Whitening in time and color; Robust coding
  • Dong & Atick: spatiotemporal power spectrum of natural movies
  • Ruderman: statistics of cone responses
  • Karklin & Simoncelli: noisy population coding of natural images
Feb. 17 ** Holiday **
Feb. 24 ICA and sparse coding
  • Barlow (1972)
  • Olshausen & Field (1997)
  • Bell & Sejnowski (1997)
March 3 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 10 Higher-order group structure
  • Geisler: contour statistics
  • Hyvarinen: subspace ICA/topgraphic ICA
  • Lyu & Simoncelli: radial Gaussianization
March 17 Energy-based models
  • Osindero & Hinton
  • Roth & Black
March 24 Learning invariances through 'slow feature analysis'
  • Foldiak/Wiskott: slow feature analysis
  • Hyvarinen: 'Bubbles'
  • Berkes et al.
March 31 ** Spring recess **
April 7 Manifold and Lie group models
April 14 Hierarchical models
  • Shan & Cottrell: stacked ICA
April 21 Deep network models
April 28
May 5
May 12