Multigradient-based convolutional neural network

Seongyoun Woo; Chulhee Lee

doi:10.1109/ICIT.2019.8755091

Multigradient-based convolutional neural network

Seongyoun Woo, Chulhee Lee

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The convolutional neural network (CNN) is a promising algorithm for artificial intelligence. Although it was developed for image classification, much research is currently in progress in various fields, such as object detection and image processing. The basic principle of the CNN, especially for classification, is to adopt a loss function and minimize it in an iterative way. In this paper, a multigradient-based training algorithm is proposed for image classification. The proposed algorithm defines an object function based on multigradients and trains the CNN by maximizing the corresponding objective function. When applied to open access databases, the proposed algorithm performed better than conventional back-propagation based CNN methods.

Original language	English
Title of host publication	Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	883-886
Number of pages	4
ISBN (Electronic)	9781538663769
DOIs	https://doi.org/10.1109/ICIT.2019.8755091
Publication status	Published - 2019 Feb
Event	2019 IEEE International Conference on Industrial Technology, ICIT 2019 - Melbourne, Australia Duration: 2019 Feb 13 → 2019 Feb 15

Publication series

Name	Proceedings of the IEEE International Conference on Industrial Technology
Volume	2019-February

Conference

Conference	2019 IEEE International Conference on Industrial Technology, ICIT 2019
Country	Australia
City	Melbourne
Period	19/2/13 → 19/2/15

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

All Science Journal Classification (ASJC) codes

Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/ICIT.2019.8755091

Fingerprint Dive into the research topics of 'Multigradient-based convolutional neural network'. Together they form a unique fingerprint.

Cite this

Woo, S., & Lee, C. (2019). Multigradient-based convolutional neural network. In Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019 (pp. 883-886). [8755091] (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2019-February). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIT.2019.8755091

@inproceedings{c8fd36ab0e2a46958c420625d87ee8b1,

title = "Multigradient-based convolutional neural network",

abstract = "The convolutional neural network (CNN) is a promising algorithm for artificial intelligence. Although it was developed for image classification, much research is currently in progress in various fields, such as object detection and image processing. The basic principle of the CNN, especially for classification, is to adopt a loss function and minimize it in an iterative way. In this paper, a multigradient-based training algorithm is proposed for image classification. The proposed algorithm defines an object function based on multigradients and trains the CNN by maximizing the corresponding objective function. When applied to open access databases, the proposed algorithm performed better than conventional back-propagation based CNN methods.",

author = "Seongyoun Woo and Chulhee Lee",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Industrial Technology, ICIT 2019 ; Conference date: 13-02-2019 Through 15-02-2019",

year = "2019",

month = feb,

doi = "10.1109/ICIT.2019.8755091",

language = "English",

series = "Proceedings of the IEEE International Conference on Industrial Technology",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "883--886",

booktitle = "Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019",

address = "United States",

}

Woo, S & Lee, C 2019, Multigradient-based convolutional neural network. in Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019., 8755091, Proceedings of the IEEE International Conference on Industrial Technology, vol. 2019-February, Institute of Electrical and Electronics Engineers Inc., pp. 883-886, 2019 IEEE International Conference on Industrial Technology, ICIT 2019, Melbourne, Australia, 19/2/13. https://doi.org/10.1109/ICIT.2019.8755091

Multigradient-based convolutional neural network. / Woo, Seongyoun; Lee, Chulhee.

Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 883-886 8755091 (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2019-February).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multigradient-based convolutional neural network

AU - Woo, Seongyoun

AU - Lee, Chulhee

PY - 2019/2

Y1 - 2019/2

N2 - The convolutional neural network (CNN) is a promising algorithm for artificial intelligence. Although it was developed for image classification, much research is currently in progress in various fields, such as object detection and image processing. The basic principle of the CNN, especially for classification, is to adopt a loss function and minimize it in an iterative way. In this paper, a multigradient-based training algorithm is proposed for image classification. The proposed algorithm defines an object function based on multigradients and trains the CNN by maximizing the corresponding objective function. When applied to open access databases, the proposed algorithm performed better than conventional back-propagation based CNN methods.

AB - The convolutional neural network (CNN) is a promising algorithm for artificial intelligence. Although it was developed for image classification, much research is currently in progress in various fields, such as object detection and image processing. The basic principle of the CNN, especially for classification, is to adopt a loss function and minimize it in an iterative way. In this paper, a multigradient-based training algorithm is proposed for image classification. The proposed algorithm defines an object function based on multigradients and trains the CNN by maximizing the corresponding objective function. When applied to open access databases, the proposed algorithm performed better than conventional back-propagation based CNN methods.

UR - http://www.scopus.com/inward/record.url?scp=85069049694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069049694&partnerID=8YFLogxK

U2 - 10.1109/ICIT.2019.8755091

DO - 10.1109/ICIT.2019.8755091

M3 - Conference contribution

AN - SCOPUS:85069049694

T3 - Proceedings of the IEEE International Conference on Industrial Technology

SP - 883

EP - 886

BT - Proceedings - 2019 IEEE International Conference on Industrial Technology, ICIT 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Industrial Technology, ICIT 2019

Y2 - 13 February 2019 through 15 February 2019

ER -

Multigradient-based convolutional neural network

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this