B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification

In this work, a Binary Quantized Convolution neural network for image classification is trained and evaluated. Binarized neural networks reduce the amount of memory, and it is possible to implement them with less hardware than those that use real value variables (Floating Point 32 bits). This type o...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Urbano Pintos, Nicolás, Lacomi, Héctor, Lavorato, Mario
Formato: Artículo publishedVersion
Lenguaje:Español
Publicado: FIUBA 2022
Materias:
Convolution Neural Network
Classification
Quantization
Redes Neuronales de Convolución
Clasificación
Cuantización
Acceso en línea:https://elektron.fi.uba.ar/elektron/article/view/169
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=169_oai
Aporte de:
Repositorio Digital de la Universidad de Buenos Aires (UBA) de Universidad de Buenos Aires
id I28-R145-169_oai
record_format dspace
spelling I28-R145-169_oai2026-02-11 Urbano Pintos, Nicolás Lacomi, Héctor Lavorato, Mario 2022-12-15 In this work, a Binary Quantized Convolution neural network for image classification is trained and evaluated. Binarized neural networks reduce the amount of memory, and it is possible to implement them with less hardware than those that use real value variables (Floating Point 32 bits). This type of network can be implemented in embedded systems, such as FPGA. A quantization-aware training was performed, to compensate for the errors caused by the loss of precision of the parameters. The model obtained an evaluation accuracy of 88% with the CIFAR-10 evaluation set. En este trabajo se entrena y evalúa una red neuronal de convolución cuantizada de forma binaria para la clasificación de imágenes. Las redes neuronales binarizadas reducen la cantidad de memoria, y es posible implementarlas con menor hardware que las redes que utilizan variables de valor real (Floating Point 32 bits). Este tipo de redes se pueden implementar en sistemas embebidos, como FPGA. Se realizó una cuantización consciente del entrenamiento, de modo de poder compensar los errores provocados por la pérdida de precisión de los parámetros. El modelo obtuvo una precisión de evaluación de un 88% con el conjunto de evaluación de CIFAR-10. application/pdf text/html https://elektron.fi.uba.ar/elektron/article/view/169 10.37537/rev.elektron.6.2.169.2022 spa FIUBA https://elektron.fi.uba.ar/elektron/article/view/169/302 https://elektron.fi.uba.ar/elektron/article/view/169/319 Derechos de autor 2022 Nicolás Urbano Pintos Elektron Journal; Vol. 6 No. 2 (2022); 107-114 Revista Elektron; Vol. 6 Núm. 2 (2022); 107-114 Revista Elektron; v. 6 n. 2 (2022); 107-114 2525-0159 2525-0159 Convolution Neural Network Classification Quantization Redes Neuronales de Convolución Clasificación Cuantización B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification B-VGG16: Red Neuronal de Convolución cuantizada binariamente para la clasificación de imágenes info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=169_oai
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-145
collection Repositorio Digital de la Universidad de Buenos Aires (UBA)
language Español
orig_language_str_mv spa
topic Convolution Neural Network
Classification
Quantization
Redes Neuronales de Convolución
Clasificación
Cuantización
spellingShingle Convolution Neural Network
Classification
Quantization
Redes Neuronales de Convolución
Clasificación
Cuantización
Urbano Pintos, Nicolás
Lacomi, Héctor
Lavorato, Mario
B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
topic_facet Convolution Neural Network
Classification
Quantization
Redes Neuronales de Convolución
Clasificación
Cuantización
description In this work, a Binary Quantized Convolution neural network for image classification is trained and evaluated. Binarized neural networks reduce the amount of memory, and it is possible to implement them with less hardware than those that use real value variables (Floating Point 32 bits). This type of network can be implemented in embedded systems, such as FPGA. A quantization-aware training was performed, to compensate for the errors caused by the loss of precision of the parameters. The model obtained an evaluation accuracy of 88% with the CIFAR-10 evaluation set.
format Artículo
publishedVersion
author Urbano Pintos, Nicolás
Lacomi, Héctor
Lavorato, Mario
author_facet Urbano Pintos, Nicolás
Lacomi, Héctor
Lavorato, Mario
author_sort Urbano Pintos, Nicolás
title B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
title_short B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
title_full B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
title_fullStr B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
title_full_unstemmed B-VGG16: Binary Quantized Convolutional Neuronal Network for image classification
title_sort b-vgg16: binary quantized convolutional neuronal network for image classification
publisher FIUBA
publishDate 2022
url https://elektron.fi.uba.ar/elektron/article/view/169
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=169_oai
work_keys_str_mv AT urbanopintosnicolas bvgg16binaryquantizedconvolutionalneuronalnetworkforimageclassification
AT lacomihector bvgg16binaryquantizedconvolutionalneuronalnetworkforimageclassification
AT lavoratomario bvgg16binaryquantizedconvolutionalneuronalnetworkforimageclassification
AT urbanopintosnicolas bvgg16redneuronaldeconvolucioncuantizadabinariamenteparalaclasificaciondeimagenes
AT lacomihector bvgg16redneuronaldeconvolucioncuantizadabinariamenteparalaclasificaciondeimagenes
AT lavoratomario bvgg16redneuronaldeconvolucioncuantizadabinariamenteparalaclasificaciondeimagenes
_version_ 1859522232904056832

Ejemplares similares