An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F20%3A10246263" target="_blank" >RIV/61989100:27240/20:10246263 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-50097-9_10" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-50097-9_10</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-50097-9_10" target="_blank" >10.1007/978-3-030-50097-9_10</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST)

Popis výsledku v původním jazyce

Recently, Convolutional Neural Networks (CNN) has been used in variety of domains, including fashion classification. Social media, e-commerce, and criminal law are extensively applicable in this field. CNNs are efficient to train and found to give the most accurate results in solving real world problems. In this paper, we use Fashion MNIST dataset for evaluating the performance of convolutional neural network based deep learning architectures. We compare most common deep learning architectures such as AlexNet, GoogleNet, VGG, ResNet, DenseNet and SqueezeNet to find the best performance. We additionally propose a simple modification to the architecture to improve and accelerate learning process. We report accuracy measurements (93.43%) and the value of loss function (0.19) using our proposed method and show its significant improvements over other architectures.

Název v anglickém jazyce

An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST)

Popis výsledku anglicky

Recently, Convolutional Neural Networks (CNN) has been used in variety of domains, including fashion classification. Social media, e-commerce, and criminal law are extensively applicable in this field. CNNs are efficient to train and found to give the most accurate results in solving real world problems. In this paper, we use Fashion MNIST dataset for evaluating the performance of convolutional neural network based deep learning architectures. We compare most common deep learning architectures such as AlexNet, GoogleNet, VGG, ResNet, DenseNet and SqueezeNet to find the best performance. We additionally propose a simple modification to the architecture to improve and accelerate learning process. We report accuracy measurements (93.43%) and the value of loss function (0.19) using our proposed method and show its significant improvements over other architectures.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advances in Intelligent Systems and Computing. Volume 1156

ISBN

978-3-030-50096-2

ISSN

2194-5357

e-ISSN

2194-5365

Počet stran výsledku

11

Strana od-do

85-95

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Ostrava

Datum konání akce

2. 12. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000590145400010