Differences between revisions 35 and 36
Revision 35 as of 2013-09-12 07:54:12
Size: 2405
Comment:
Revision 36 as of 2013-09-12 07:55:18
Size: 2400
Comment:
Deletions are marked like this. Additions are marked like this.
Line 3: Line 3:
 
Line 17: Line 16:
##<<Include(Figures/Perrinet02sparse/FigureDeux)>> <<Include(Figures/Perrinet02sparse/FigureDeux)>>

Sparse spike coding in an asynchronous feed-forward multi-layer neural network using Matching Pursuit

This paper introduced for the first time the use of Matching Pursuit in a neuromimetic architecture of low-level visual areas. It aims at understanding the efficiency and generality of correlation-based inhibition propagation, by showing:

  • the link between sparse coding, spike coding and matching pursuit,
  • the use of a quantization in Matching Pursuit (see Fig. 1),

  • the efficiency of this algorithm (e.g. for compression as compared with JPEG see Fig. 2) -- this was developped in (Perrinet, 03, IEEE) and (Fischer, 07)),

  • that a Sparse Hebbian Learning scheme could be applied, leading to the learning of edge-like filter (this is the first report of using an adaptive matching pursuit scheme to my knowledge) -- this was developped in (Perrinet, 03, IEEE) and (Fischer, 07)), 

  • the possible use as a model of low-level saliency.

See also 

Perrinet02esann_2.jpg

Figure 2: (A) Look-Up-Table : mean and variance of the absolute contrast in function of the relative rank for a database of 100 natural images (B) Comparison of MSE in function of the file size (in ) for the different methods : (a) MP; (b) MP with Look-Up-Table; (c) JPEG at different qualities.

reference

  • Laurent Perrinet, Manuel Samuelides, Simon Thorpe. Sparse spike coding in an asynchronous feed-forward multi-layer neural network using Matching Pursuit., URL . Neurocomputing, 57C:125--34, 2002,  abstract.


All material (c) L. Perrinet. Please check the copyright notice.


TagPublicationsArticles TagSparse

welcome: please sign in