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...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	András Lörincz, Zsolt Palotai, Gábor Szirtes
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2012
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/fcc25e19051f45d9b8fedf6e8f4a0889
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fcc25e19051f45d9b8fedf6e8f4a0889
record_format	dspace
spelling	oai:doaj.org-article:fcc25e19051f45d9b8fedf6e8f4a08892021-11-18T05:51:33ZEfficient sparse coding in early sensory processing: lessons from signal recovery.1553-734X1553-735810.1371/journal.pcbi.1002372https://doaj.org/article/fcc25e19051f45d9b8fedf6e8f4a08892012-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/22396629/pdf/?tool=EBIhttps://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358Sensory 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.András LörinczZsolt PalotaiGábor SzirtesPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 8, Iss 3, p e1002372 (2012)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 András Lörincz Zsolt Palotai Gábor Szirtes Efficient sparse coding in early sensory processing: lessons from signal recovery.
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	article
author	András Lörincz Zsolt Palotai Gábor Szirtes
author_facet	András Lörincz Zsolt Palotai Gábor Szirtes
author_sort	András Lörincz
title	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_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_sort	efficient sparse coding in early sensory processing: lessons from signal recovery.
publisher	Public Library of Science (PLoS)
publishDate	2012
url	https://doaj.org/article/fcc25e19051f45d9b8fedf6e8f4a0889
work_keys_str_mv	AT andraslorincz efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery AT zsoltpalotai efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery AT gaborszirtes efficientsparsecodinginearlysensoryprocessinglessonsfromsignalrecovery
_version_	1718424766909513728

Efficient sparse coding in early sensory processing: lessons from signal recovery.

Ejemplares similares