An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST)
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
An Analysis of Convolutional Neural Network for Fashion Images Classification (Fashion-MNIST)
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Advances in Intelligent Systems and Computing. Volume 1156
ISBN
978-3-030-50096-2
ISSN
2194-5357
e-ISSN
2194-5365
Number of pages
11
Pages from-to
85-95
Publisher name
Springer
Place of publication
Cham
Event location
Ostrava
Event date
Dec 2, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000590145400010