A high-throughput screening approach to discovering good forms of biologically inspired visual representation.

While many models of biological object recognition share a common set of "broad-stroke" properties, the performance of any one model depends strongly on the choice of parameters in a particular instantiation of that model--e.g., the number of units per layer, the size of pooling kernels, e...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nicolas Pinto, David Doukhan, James J DiCarlo, David D Cox
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2009
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/4e67946dd96542668d5d9543e5c9af31
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4e67946dd96542668d5d9543e5c9af31
record_format	dspace
spelling	oai:doaj.org-article:4e67946dd96542668d5d9543e5c9af312021-11-25T05:42:49ZA high-throughput screening approach to discovering good forms of biologically inspired visual representation.1553-734X1553-735810.1371/journal.pcbi.1000579https://doaj.org/article/4e67946dd96542668d5d9543e5c9af312009-11-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/19956750/pdf/?tool=EBIhttps://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358While many models of biological object recognition share a common set of "broad-stroke" properties, the performance of any one model depends strongly on the choice of parameters in a particular instantiation of that model--e.g., the number of units per layer, the size of pooling kernels, exponents in normalization operations, etc. Since the number of such parameters (explicit or implicit) is typically large and the computational cost of evaluating one particular parameter set is high, the space of possible model instantiations goes largely unexplored. Thus, when a model fails to approach the abilities of biological visual systems, we are left uncertain whether this failure is because we are missing a fundamental idea or because the correct "parts" have not been tuned correctly, assembled at sufficient scale, or provided with enough training. Here, we present a high-throughput approach to the exploration of such parameter sets, leveraging recent advances in stream processing hardware (high-end NVIDIA graphic cards and the PlayStation 3's IBM Cell Processor). In analogy to high-throughput screening approaches in molecular biology and genetics, we explored thousands of potential network architectures and parameter instantiations, screening those that show promising object recognition performance for further analysis. We show that this approach can yield significant, reproducible gains in performance across an array of basic object recognition tasks, consistently outperforming a variety of state-of-the-art purpose-built vision systems from the literature. As the scale of available computational power continues to expand, we argue that this approach has the potential to greatly accelerate progress in both artificial vision and our understanding of the computational underpinning of biological vision.Nicolas PintoDavid DoukhanJames J DiCarloDavid D CoxPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 5, Iss 11, p e1000579 (2009)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Nicolas Pinto David Doukhan James J DiCarlo David D Cox A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
description	While many models of biological object recognition share a common set of "broad-stroke" properties, the performance of any one model depends strongly on the choice of parameters in a particular instantiation of that model--e.g., the number of units per layer, the size of pooling kernels, exponents in normalization operations, etc. Since the number of such parameters (explicit or implicit) is typically large and the computational cost of evaluating one particular parameter set is high, the space of possible model instantiations goes largely unexplored. Thus, when a model fails to approach the abilities of biological visual systems, we are left uncertain whether this failure is because we are missing a fundamental idea or because the correct "parts" have not been tuned correctly, assembled at sufficient scale, or provided with enough training. Here, we present a high-throughput approach to the exploration of such parameter sets, leveraging recent advances in stream processing hardware (high-end NVIDIA graphic cards and the PlayStation 3's IBM Cell Processor). In analogy to high-throughput screening approaches in molecular biology and genetics, we explored thousands of potential network architectures and parameter instantiations, screening those that show promising object recognition performance for further analysis. We show that this approach can yield significant, reproducible gains in performance across an array of basic object recognition tasks, consistently outperforming a variety of state-of-the-art purpose-built vision systems from the literature. As the scale of available computational power continues to expand, we argue that this approach has the potential to greatly accelerate progress in both artificial vision and our understanding of the computational underpinning of biological vision.
format	article
author	Nicolas Pinto David Doukhan James J DiCarlo David D Cox
author_facet	Nicolas Pinto David Doukhan James J DiCarlo David D Cox
author_sort	Nicolas Pinto
title	A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
title_short	A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
title_full	A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
title_fullStr	A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
title_full_unstemmed	A high-throughput screening approach to discovering good forms of biologically inspired visual representation.
title_sort	high-throughput screening approach to discovering good forms of biologically inspired visual representation.
publisher	Public Library of Science (PLoS)
publishDate	2009
url	https://doaj.org/article/4e67946dd96542668d5d9543e5c9af31
work_keys_str_mv	AT nicolaspinto ahighthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT daviddoukhan ahighthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT jamesjdicarlo ahighthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT daviddcox ahighthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT nicolaspinto highthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT daviddoukhan highthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT jamesjdicarlo highthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation AT daviddcox highthroughputscreeningapproachtodiscoveringgoodformsofbiologicallyinspiredvisualrepresentation
_version_	1718414456451497984

A high-throughput screening approach to discovering good forms of biologically inspired visual representation.

Ejemplares similares