Cargando…
Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery
Sensory representations are not only sparse, but often overcomplete: coding units significantly outnumber the input units. For models of neural coding this overcompleteness poses a computational challenge for shaping the signal processing channels as well as for using the large and sparse representa...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2012
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3291527/ https://www.ncbi.nlm.nih.gov/pubmed/22396629 http://dx.doi.org/10.1371/journal.pcbi.1002372 |
_version_ | 1782225145035751424 |
---|---|
author | Lörincz, András Palotai, Zsolt Szirtes, Gábor |
author_facet | Lörincz, András Palotai, Zsolt Szirtes, Gábor |
author_sort | Lörincz, András |
collection | PubMed |
description | Sensory representations are not only sparse, but often overcomplete: coding units significantly outnumber the input units. For models of neural coding this overcompleteness poses a computational challenge for shaping the signal processing channels as well as for using the large and sparse representations in an efficient way. We argue that higher level overcompleteness becomes computationally tractable by imposing sparsity on synaptic activity and we also show that such structural sparsity can be facilitated by statistics based decomposition of the stimuli into typical and atypical parts prior to sparse coding. Typical parts represent large-scale correlations, thus they can be significantly compressed. Atypical parts, on the other hand, represent local features and are the subjects of actual sparse coding. When applied on natural images, our decomposition based sparse coding model can efficiently form overcomplete codes and both center-surround and oriented filters are obtained similar to those observed in the retina and the primary visual cortex, respectively. Therefore we hypothesize that the proposed computational architecture can be seen as a coherent functional model of the first stages of sensory coding in early vision. |
format | Online Article Text |
id | pubmed-3291527 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2012 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-32915272012-03-06 Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery Lörincz, András Palotai, Zsolt Szirtes, Gábor PLoS Comput Biol Research Article Sensory representations are not only sparse, but often overcomplete: coding units significantly outnumber the input units. For models of neural coding this overcompleteness poses a computational challenge for shaping the signal processing channels as well as for using the large and sparse representations in an efficient way. We argue that higher level overcompleteness becomes computationally tractable by imposing sparsity on synaptic activity and we also show that such structural sparsity can be facilitated by statistics based decomposition of the stimuli into typical and atypical parts prior to sparse coding. Typical parts represent large-scale correlations, thus they can be significantly compressed. Atypical parts, on the other hand, represent local features and are the subjects of actual sparse coding. When applied on natural images, our decomposition based sparse coding model can efficiently form overcomplete codes and both center-surround and oriented filters are obtained similar to those observed in the retina and the primary visual cortex, respectively. Therefore we hypothesize that the proposed computational architecture can be seen as a coherent functional model of the first stages of sensory coding in early vision. Public Library of Science 2012-03-01 /pmc/articles/PMC3291527/ /pubmed/22396629 http://dx.doi.org/10.1371/journal.pcbi.1002372 Text en Lörincz et al. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited. |
spellingShingle | Research Article Lörincz, András Palotai, Zsolt Szirtes, Gábor Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title | Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title_full | Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title_fullStr | Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title_full_unstemmed | Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title_short | Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery |
title_sort | efficient sparse coding in early sensory processing: lessons from signal recovery |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3291527/ https://www.ncbi.nlm.nih.gov/pubmed/22396629 http://dx.doi.org/10.1371/journal.pcbi.1002372 |
work_keys_str_mv | AT lorinczandras efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery AT palotaizsolt efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery AT szirtesgabor efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery |