An error based adaptive learning rate stochastic gradient descent algorithm in convolutional neural network

Research Article
Open access

An error based adaptive learning rate stochastic gradient descent algorithm in convolutional neural network

Qianyi Li 1*
  • 1 Dalian University of Technology, Dalian, Liaoning, China    
  • *corresponding author li15524867927@163.com
Published on 22 March 2023 | https://doi.org/10.54254/2755-2721/2/20220515
ACE Vol.2
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-915371-19-5
ISBN (Online): 978-1-915371-20-1

Abstract

If the learning rate of convolutional neural network (CNN) is set improperly, the efficiency and accuracy of the algorithm will be greatly affected. To solve this problem, a learning rate adaptive algorithm is proposed to improve the traditional SGD: based on parameter prediction, the historical training error is used to update the learning rate. Under the condition of given initial learning rate, experiments on classical data sets prove the effectiveness of the above algorithms, and the adaptive learning rate stochastic gradient descent algorithm can keep the convergence of the network. Training accuracy is relatively stable; Shorter training time; And improve the learning accuracy.

Keywords:

convolutional neural network, parameter prediction., stochastic gradient descent, adaptive learning rate updating al-gorithm

Li,Q. (2023). An error based adaptive learning rate stochastic gradient descent algorithm in convolutional neural network. Applied and Computational Engineering,2,345-353.
Export citation

References

[1]. Lu Hongtao, Zhang Qinchuan. Applications of deep convolutional neural network in computer vision[J]. Journal of Data Acquisition and Processing, 31(1):1-17(2016).

[2]. Sun Yanan, Lin Wenbin. Applications of gradient descent method in machine learning[J]. Journal of Suzhou University of Science and Technology (Natural Science Edition), 35(02):26-31 (2018).

[3]. Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization[J]. Journal of Machine Learning Research, 12(7):257-269 (2011).

[4]. Alex Krizhevsky, Ilya Sutskever, Hinton GE. ImagNet classification with deep convolutional neural networks[C]// Advances in Neural Information Processing System. Cambridge: MIT Press, pp.1097-1105 (2012).

[5]. Liang M, Hu X. Recurrent convolutional neural nerwork for object recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 367-3375 (2015).

[6]. Dyda R O, Hart P E, Stork D G [Author], Li Hongdong, Yao Tianxiang[Translator]. Pattern Classification. Beijing: China Machine Press, (2003).

[7]. Bouvrie J. Notes On Convolutional Neural Networks, MIT CBCL Tech Report, Cambridge, MA, (2006).

[8]. Deng Xing, Deng Zhenrong, Xu Liang, et al. Optimized collaborative filtering recommendation algorithm[J]. Computer Engineering and Design, pp.37(5): 1259-1264 (206).

[9]. Tomoumi Takase and Satoshi Oyama and Masahito Kurihara. Effective neural network training with adaptive learning rate based on training loss[J]. Neural Networks, 2018, 101: 68-78.

[10]. Duchi J, Hazan E, Singer Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[J]. Journal of Machine Learning Research, 2011, 12: 2121-2159.

[11]. King M, Diederik B, Adam J. A Method for Stochastic Optinmization[J] (2014).

[12]. Wang Changsong, Zhao Xiang. General method for evaluating optimization algorithm and its application[J]. Journal of Computer Applications, pp. 30(A01): 76-79(in Chinese) (2010).

[13]. Sutkever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning[C]// International Conference on Machine Learning, 2013: 1139-1147.

[14]. Jin Haidong, Liu Quan, Chen Donghuo. An integrated stochastic gradient descent Q-learning method with adaptive learning rate[J]. Chinese Journal of Computers, pp. 42(10): 2203-2215. (2019).

Cite this article

Li,Q. (2023). An error based adaptive learning rate stochastic gradient descent algorithm in convolutional neural network. Applied and Computational Engineering,2,345-353.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 4th International Conference on Computing and Data Science (CONF-CDS 2022)

ISBN：978-1-915371-19-5(Print) / 978-1-915371-20-1(Online)
Editor：Alan Wang
Conference website: https://www.confcds.org/
Conference date: 16 July 2022
Series: Applied and Computational Engineering
Volume number: Vol.2
ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Lu Hongtao, Zhang Qinchuan. Applications of deep convolutional neural network in computer vision[J]. Journal of Data Acquisition and Processing, 31(1):1-17(2016).

[2]. Sun Yanan, Lin Wenbin. Applications of gradient descent method in machine learning[J]. Journal of Suzhou University of Science and Technology (Natural Science Edition), 35(02):26-31 (2018).

[3]. Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization[J]. Journal of Machine Learning Research, 12(7):257-269 (2011).

[4]. Alex Krizhevsky, Ilya Sutskever, Hinton GE. ImagNet classification with deep convolutional neural networks[C]// Advances in Neural Information Processing System. Cambridge: MIT Press, pp.1097-1105 (2012).

[5]. Liang M, Hu X. Recurrent convolutional neural nerwork for object recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 367-3375 (2015).

[6]. Dyda R O, Hart P E, Stork D G [Author], Li Hongdong, Yao Tianxiang[Translator]. Pattern Classification. Beijing: China Machine Press, (2003).

[7]. Bouvrie J. Notes On Convolutional Neural Networks, MIT CBCL Tech Report, Cambridge, MA, (2006).

[8]. Deng Xing, Deng Zhenrong, Xu Liang, et al. Optimized collaborative filtering recommendation algorithm[J]. Computer Engineering and Design, pp.37(5): 1259-1264 (206).

[9]. Tomoumi Takase and Satoshi Oyama and Masahito Kurihara. Effective neural network training with adaptive learning rate based on training loss[J]. Neural Networks, 2018, 101: 68-78.

[10]. Duchi J, Hazan E, Singer Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[J]. Journal of Machine Learning Research, 2011, 12: 2121-2159.

[11]. King M, Diederik B, Adam J. A Method for Stochastic Optinmization[J] (2014).

[12]. Wang Changsong, Zhao Xiang. General method for evaluating optimization algorithm and its application[J]. Journal of Computer Applications, pp. 30(A01): 76-79(in Chinese) (2010).

[13]. Sutkever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning[C]// International Conference on Machine Learning, 2013: 1139-1147.

[14]. Jin Haidong, Liu Quan, Chen Donghuo. An integrated stochastic gradient descent Q-learning method with adaptive learning rate[J]. Chinese Journal of Computers, pp. 42(10): 2203-2215. (2019).

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.