A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.

The brain mechanism of extracting visual features for recognizing various objects has consistently been a controversial issue in computational models of object recognition. To extract visual features, we introduce a new, biologically motivated model for facial categorization, which is an extension o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Karim Rajaei, Seyed-Mahdi Khaligh-Razavi, Masoud Ghodrati, Reza Ebrahimpour, Mohammad Ebrahim Shiri Ahmad Abadi
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2012
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/a95a8c8f8a6a44eb904873f5b4a41f52
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a95a8c8f8a6a44eb904873f5b4a41f52
record_format	dspace
spelling	oai:doaj.org-article:a95a8c8f8a6a44eb904873f5b4a41f522021-11-18T07:15:38ZA stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.1932-620310.1371/journal.pone.0038478https://doaj.org/article/a95a8c8f8a6a44eb904873f5b4a41f522012-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/22719892/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203The brain mechanism of extracting visual features for recognizing various objects has consistently been a controversial issue in computational models of object recognition. To extract visual features, we introduce a new, biologically motivated model for facial categorization, which is an extension of the Hubel and Wiesel simple-to-complex cell hierarchy. To address the synaptic stability versus plasticity dilemma, we apply the Adaptive Resonance Theory (ART) for extracting informative intermediate level visual features during the learning process, which also makes this model stable against the destruction of previously learned information while learning new information. Such a mechanism has been suggested to be embedded within known laminar microcircuits of the cerebral cortex. To reveal the strength of the proposed visual feature learning mechanism, we show that when we use this mechanism in the training process of a well-known biologically motivated object recognition model (the HMAX model), it performs better than the HMAX model in face/non-face classification tasks. Furthermore, we demonstrate that our proposed mechanism is capable of following similar trends in performance as humans in a psychophysical experiment using a face versus non-face rapid categorization task.Karim RajaeiSeyed-Mahdi Khaligh-RazaviMasoud GhodratiReza EbrahimpourMohammad Ebrahim Shiri Ahmad AbadiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 7, Iss 6, p e38478 (2012)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Karim Rajaei Seyed-Mahdi Khaligh-Razavi Masoud Ghodrati Reza Ebrahimpour Mohammad Ebrahim Shiri Ahmad Abadi A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
description	The brain mechanism of extracting visual features for recognizing various objects has consistently been a controversial issue in computational models of object recognition. To extract visual features, we introduce a new, biologically motivated model for facial categorization, which is an extension of the Hubel and Wiesel simple-to-complex cell hierarchy. To address the synaptic stability versus plasticity dilemma, we apply the Adaptive Resonance Theory (ART) for extracting informative intermediate level visual features during the learning process, which also makes this model stable against the destruction of previously learned information while learning new information. Such a mechanism has been suggested to be embedded within known laminar microcircuits of the cerebral cortex. To reveal the strength of the proposed visual feature learning mechanism, we show that when we use this mechanism in the training process of a well-known biologically motivated object recognition model (the HMAX model), it performs better than the HMAX model in face/non-face classification tasks. Furthermore, we demonstrate that our proposed mechanism is capable of following similar trends in performance as humans in a psychophysical experiment using a face versus non-face rapid categorization task.
format	article
author	Karim Rajaei Seyed-Mahdi Khaligh-Razavi Masoud Ghodrati Reza Ebrahimpour Mohammad Ebrahim Shiri Ahmad Abadi
author_facet	Karim Rajaei Seyed-Mahdi Khaligh-Razavi Masoud Ghodrati Reza Ebrahimpour Mohammad Ebrahim Shiri Ahmad Abadi
author_sort	Karim Rajaei
title	A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
title_short	A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
title_full	A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
title_fullStr	A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
title_full_unstemmed	A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
title_sort	stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.
publisher	Public Library of Science (PLoS)
publishDate	2012
url	https://doaj.org/article/a95a8c8f8a6a44eb904873f5b4a41f52
work_keys_str_mv	AT karimrajaei astablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT seyedmahdikhalighrazavi astablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT masoudghodrati astablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT rezaebrahimpour astablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT mohammadebrahimshiriahmadabadi astablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT karimrajaei stablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT seyedmahdikhalighrazavi stablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT masoudghodrati stablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT rezaebrahimpour stablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization AT mohammadebrahimshiriahmadabadi stablebiologicallymotivatedlearningmechanismforvisualfeatureextractiontohandlefacialcategorization
_version_	1718423747014164480

A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization.

Ejemplares similares