Algorithm Research on Improving Activation Function of Convolutional Neural Networks

被引：0
|
作者：
Guo, Yanhua [1 ]
Sun, Lei [1 ]
Zhang, Zhihong [2 ]
He, Hong [1 ]
机构：
[1] Tianjin Univ Technol, Sch Elect Engn & Automat, Tianjin Key Lab Control Theory & Applicat Complic, Tianjin 300384, Peoples R China
[2] Tianjin Inst Elect Technol, Tianjin 300232, Peoples R China
来源：
PROCEEDINGS OF THE 2019 31ST CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2019) | 2019年
关键词：
Deep Learning; Convolutional Neural Networks; Activation function; Image classification;
D O I：
10.1109/ccdc.2019.8833156
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Aiming at the slow convergence of t he activation function of Sigmoid, Tanh, ReLu and Softplus as the model and the non-convergence caused by gradient dispersion, this paper proposes an algorithm to improve the activation function of convolutional neural network. UsingR-SReLU as the activation function of the neural network, the convergence speed of various excitation functions to the network and the accuracy of image recognition are analyzed. The experimental data shows that the improved activation function R-SReLU not only has a fast convergence speed, but also has a small error rate, and can improve the accuracy of classification more effectively. The maximum recognition accuracy reaches 88.03%.
引用
收藏
页码：3582 / 3586
页数：5
相关论文
共 50 条
  • [21] Improving the Performance of Convolutional Neural Networks for Image Classification
    Giveki, Davar
    OPTICAL MEMORY AND NEURAL NETWORKS, 2021, 30 (01) : 51 - 66
  • [22] Improving efficiency in convolutional neural networks with multilinear filters
    Dat Thanh Tran
    Iosifidis, Alexandros
    Gabbouj, Moncef
    NEURAL NETWORKS, 2018, 105 : 328 - 339
  • [23] Strategies for Improving the Error Robustness of Convolutional Neural Networks
    Morais, Antonio
    Barbosa, Raul
    Lourenco, Nuno
    Cerveira, Frederico
    Lombardi, Michele
    Madeira, Henrique
    2022 IEEE 22ND INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY, QRS, 2022, : 874 - 883
  • [24] Convolutional neural networks and the modulation transfer function
    King, Page
    Koshel, R. John
    APPLICATIONS OF MACHINE LEARNING 2023, 2023, 12675
  • [25] Research About Algorithm and Application of Tunable Activation Function Neural Network
    Wang, Zhengwu
    Cui, Hang
    PROCEEDINGS OF THE FIRST SYMPOSIUM ON AVIATION MAINTENANCE AND MANAGEMENT-VOL II, 2014, 297 : 55 - 61
  • [26] Review of research on lightweight convolutional neural networks
    Zhou, Yan
    Chen, Shaochang
    Wang, Yiming
    Huan, Wenming
    PROCEEDINGS OF 2020 IEEE 5TH INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC 2020), 2020, : 1713 - 1720
  • [27] Research on Principle and Application of Convolutional Neural Networks
    Zhou, Hang
    Sun, Qichen
    2019 5TH INTERNATIONAL CONFERENCE ON ENVIRONMENTAL SCIENCE AND MATERIAL APPLICATION, 2020, 440
  • [28] Progress in Interpretability Research of Convolutional Neural Networks
    Zhang, Wei
    Cai, Lizhi
    Chen, Mingang
    Wang, Naiqi
    MOBILE COMPUTING, APPLICATIONS, AND SERVICES, MOBICASE 2019, 2019, 290 : 155 - 168
  • [29] Improving Rainfall Forecasting via Radial Basis Function and Deep Convolutional Neural Networks Integration
    Hemalatha, J.
    Vivek, V.
    Sekar, M.
    Devi, M. K. Kavitha
    JOURNAL OF CLIMATE CHANGE, 2023, 9 (04) : 37 - 43
  • [30] Periodic Function as Activation Function for Neural Networks
    Xu, Ding
    Guan, Yue
    Cai, Ping-ping
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE: TECHNIQUES AND APPLICATIONS, AITA 2016, 2016, : 179 - 183
12345