Differences between revisions 32 and 33
Revision 32 as of 2013-09-12 07:51:49
Size: 2570
Comment:
Revision 33 as of 2013-09-12 07:53:24
Size: 2427
Comment:
Deletions are marked like this. Additions are marked like this.
Line 21: Line 21:

Line 30: Line 32:
        Author = {Perrinet, Laurent and Samuelides, Manuel and Thorpe, Simon},
        Journal = {Neurocomputing},
        Pages = {125--34},
Line 41: Line 42:
TagPublicationsArticles TagSparse

---- /!\ '''End of edit conflict''' ----
TagPublicationsArticles

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 

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 + 125--34, 2002,  abstract.


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


TagPublicationsArticles

welcome: please sign in