Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)

<Previous Article In Volume
Next Article In Volume>

Exploration of Neural Network Optimization Methods Based on LeNet-5

Authors
Yifang Pang1, *
1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
*Corresponding author. Email: 2020080602018@std.uestc.edu.cn
Corresponding Author
Yifang Pang
Available Online 27 November 2023.
DOI
10.2991/978-94-6463-300-9_75How to use a DOI?
Keywords
Deep Learning; LeNet-5; Dropout; Attention; Neural Network
ABSTRACT

In today’s society, the application of artificial neural networks in the field of image classification is becoming increasingly widespread. However, the exploration of how to improve the classification accuracy of neural networks has never stopped. This paper is based on the most classic neural network LeNet-5 and proposes three methods to optimize the network, observing its classification performance on the image dataset. The three methods are to increase network depth, add dropout mechanism, and use CBAM attention mechanism. For the experimental indicators, this paper chooses to use the Loss function, accuracy and recall to verify the effect of image classification. After comparing the experimental results, this paper draws the corresponding Line chart to observe the change trend, and conducts visual clustering analysis of the accuracy of each category classification. Finally, this work found that all three corresponding optimization methods have an improvement effect on the network, with the dropout and Attention mechanisms being the most obvious.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
Series
Advances in Computer Science Research
Publication Date
27 November 2023
ISBN
10.2991/978-94-6463-300-9_75
ISSN
2352-538X
DOI
10.2991/978-94-6463-300-9_75How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Yifang Pang
PY  - 2023
DA  - 2023/11/27
TI  - Exploration of Neural Network Optimization Methods Based on LeNet-5
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 713
EP  - 722
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_75
DO  - 10.2991/978-94-6463-300-9_75
ID  - Pang2023
ER  -