English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Slowness and sparseness have diverging effects on complex cell learning

Lies, J.-P., Häfner, R., & Bethge, M. (2014). Slowness and sparseness have diverging effects on complex cell learning. PLoS Computational Biology, 10(3), 1-11. doi:10.1371/journal.pcbi.1003468.

Item is

Files

show Files

Creators

show
hide
 Creators:
Lies, J-P, Author              
Häfner, RM, Author              
Bethge, M1, 2, Author              
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Following earlier studies which showed that a sparse coding principle may explain the receptive field properties of complex cells in primary visual cortex, it has been concluded that the same properties may be equally derived from a slowness principle. In contrast to this claim, we here show that slowness and sparsity drive the representations towards substantially different receptive field properties. To do so, we present complete sets of basis functions learned with slow subspace analysis (SSA) in case of natural movies as well as translations, rotations, and scalings of natural images. SSA directly parallels independent subspace analysis (ISA) with the only difference that SSA maximizes slowness instead of sparsity. We find a large discrepancy between the filter shapes learned with SSA and ISA. We argue that SSA can be understood as a generalization of the Fourier transform where the power spectrum corresponds to the maximally slow subspace energies in SSA. Finally, we investigate the trade-off between slowness and sparseness when combined in one objective function.

Details

show
hide
Language(s):
 Dates: 2014-03
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1371/journal.pcbi.1003468
eDoc: e1003468
BibTex Citekey: LiesHB2014
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: PLoS Computational Biology
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 10 (3) Sequence Number: - Start / End Page: 1 - 11 Identifier: -