Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks

Convolutional Neural Networks (CNN) are often unsuitable for predictive modeling involving nonimage based biological features. Here, the authors present a mapping termed REFINED to represent high dimensional vectors as compact images with spatial correlation that makes it compatible with CNN based l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Omid Bazgir, Ruibo Zhang, Saugato Rahman Dhruba, Raziur Rahman, Souparno Ghosh, Ranadip Pal
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/6277e3dea67843cfa33738444ad4f63f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6277e3dea67843cfa33738444ad4f63f
record_format	dspace
spelling	oai:doaj.org-article:6277e3dea67843cfa33738444ad4f63f2021-12-02T19:09:54ZRepresentation of features as images with neighborhood dependencies for compatibility with convolutional neural networks10.1038/s41467-020-18197-y2041-1723https://doaj.org/article/6277e3dea67843cfa33738444ad4f63f2020-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-18197-yhttps://doaj.org/toc/2041-1723Convolutional Neural Networks (CNN) are often unsuitable for predictive modeling involving nonimage based biological features. Here, the authors present a mapping termed REFINED to represent high dimensional vectors as compact images with spatial correlation that makes it compatible with CNN based learning.Omid BazgirRuibo ZhangSaugato Rahman DhrubaRaziur RahmanSouparno GhoshRanadip PalNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-13 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Omid Bazgir Ruibo Zhang Saugato Rahman Dhruba Raziur Rahman Souparno Ghosh Ranadip Pal Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
description	Convolutional Neural Networks (CNN) are often unsuitable for predictive modeling involving nonimage based biological features. Here, the authors present a mapping termed REFINED to represent high dimensional vectors as compact images with spatial correlation that makes it compatible with CNN based learning.
format	article
author	Omid Bazgir Ruibo Zhang Saugato Rahman Dhruba Raziur Rahman Souparno Ghosh Ranadip Pal
author_facet	Omid Bazgir Ruibo Zhang Saugato Rahman Dhruba Raziur Rahman Souparno Ghosh Ranadip Pal
author_sort	Omid Bazgir
title	Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
title_short	Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
title_full	Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
title_fullStr	Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
title_full_unstemmed	Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
title_sort	representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/6277e3dea67843cfa33738444ad4f63f
work_keys_str_mv	AT omidbazgir representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks AT ruibozhang representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks AT saugatorahmandhruba representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks AT raziurrahman representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks AT souparnoghosh representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks AT ranadippal representationoffeaturesasimageswithneighborhooddependenciesforcompatibilitywithconvolutionalneuralnetworks
_version_	1718377090328297472

Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks

Ejemplares similares