Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)

Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modeling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modeling of image object repre...

Descripción completa

Detalles Bibliográficos
Autores principales: Dong, Qiulei, Liu, Bo, Hu, Zhanyi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7235366/
https://www.ncbi.nlm.nih.gov/pubmed/32477087
http://dx.doi.org/10.3389/fncom.2020.00035
_version_ 1783535951443656704
author Dong, Qiulei
Liu, Bo
Hu, Zhanyi
author_facet Dong, Qiulei
Liu, Bo
Hu, Zhanyi
author_sort Dong, Qiulei
collection PubMed
description Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modeling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modeling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modeling approach, and invites due attention to be taken in practice.
format Online
Article
Text
id pubmed-7235366
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-72353662020-05-29 Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN) Dong, Qiulei Liu, Bo Hu, Zhanyi Front Comput Neurosci Neuroscience Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modeling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modeling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modeling approach, and invites due attention to be taken in practice. Frontiers Media S.A. 2020-05-12 /pmc/articles/PMC7235366/ /pubmed/32477087 http://dx.doi.org/10.3389/fncom.2020.00035 Text en Copyright © 2020 Dong, Liu and Hu. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Dong, Qiulei
Liu, Bo
Hu, Zhanyi
Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title_full Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title_fullStr Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title_full_unstemmed Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title_short Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
title_sort non-uniqueness phenomenon of object representation in modeling it cortex by deep convolutional neural network (dcnn)
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7235366/
https://www.ncbi.nlm.nih.gov/pubmed/32477087
http://dx.doi.org/10.3389/fncom.2020.00035
work_keys_str_mv AT dongqiulei nonuniquenessphenomenonofobjectrepresentationinmodelingitcortexbydeepconvolutionalneuralnetworkdcnn
AT liubo nonuniquenessphenomenonofobjectrepresentationinmodelingitcortexbydeepconvolutionalneuralnetworkdcnn
AT huzhanyi nonuniquenessphenomenonofobjectrepresentationinmodelingitcortexbydeepconvolutionalneuralnetworkdcnn

Ejemplares similares