View : 75 Download: 0

Introduction to convolutional neural network using Keras; An understanding from a statistician

Title
Introduction to convolutional neural network using Keras; An understanding from a statistician
Authors
Lee H.Song J.
Ewha Authors
송종우
SCOPUS Author ID
송종우scopus
Issue Date
2019
Journal Title
Communications for Statistical Applications and Methods
ISSN
2287-7843JCR Link
Citation
Communications for Statistical Applications and Methods vol. 26, no. 6, pp. 591 - 610
Keywords
CIFAR10Convolutional neural networkDeep neural networkImage classificationKerasMachine learningMNIST
Publisher
Korean Statistical Society
Indexed
SCOPUS; KCI scopus
Document Type
Article
Abstract
Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset. © Korean Statistical Society.
DOI
10.29220/CSAM.2019.26.6.591
Appears in Collections:
자연과학대학 > 통계학전공 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE