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
  • [41] Improving code readability classification using convolutional neural networks
    Mi, Qing
    Keung, Jacky
    Xiao, Yan
    Mensah, Solomon
    Gao, Yujin
    INFORMATION AND SOFTWARE TECHNOLOGY, 2018, 104 : 60 - 71
  • [42] Improving deep convolutional neural networks with mixed maxout units
    Zhao, Hui-zhen
    Liu, Fu-xian
    Li, Long-yue
    PLOS ONE, 2017, 12 (07):
  • [43] Improving Musical Tag Annotation with Stacking and Convolutional Neural Networks
    da Silva, Juliano Donini
    Gomes da Costa, Yandre Maldonado
    Domingues, Marcos Aurelio
    PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27TH EDITION, 2020, : 393 - 398
  • [44] IMPROVING CONVOLUTIONAL RECURRENT NEURAL NETWORKS FOR SPEECH EMOTION RECOGNITION
    Meyer, Patrick
    Xu, Ziyi
    Fingscheidt, Tim
    2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 365 - 372
  • [45] Improving discrimination ability of convolutional neural networks by hybrid learning
    In-Jung Kim
    Changbeom Choi
    Sang-Heon Lee
    International Journal on Document Analysis and Recognition (IJDAR), 2016, 19 : 1 - 9
  • [46] Improving Fingerprint Indoor Localization Using Convolutional Neural Networks
    Sun, Danshi
    Wei, Erhu
    Yang, Li
    Xu, Shiyi
    IEEE ACCESS, 2020, 8 : 193396 - 193411
  • [47] Algorithm Research Based on Multi-Feature Fusion of EEG Signals with Convolutional Neural Networks
    Song, Shilin
    Zhang, Xuejun
    Computer Engineering and Applications, 2024, 60 (08) : 148 - 155
  • [48] Improving discrimination ability of convolutional neural networks by hybrid learning
    Kim, In-Jung
    Choi, Changbeom
    Lee, Sang-Heon
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2016, 19 (01) : 1 - 9
  • [49] Improving Performance of Convolutional Neural Networks via Feature Embedding
    Ghoshal, Torumoy
    Zhang, Silu
    Dang, Xin
    Wilkins, Dawn
    Chen, Yixin
    PROCEEDINGS OF THE 2019 ANNUAL ACM SOUTHEAST CONFERENCE (ACMSE 2019), 2019, : 31 - 38
  • [50] Improving accuracy of Pedestrian Detection using Convolutional Neural Networks
    Esfandiari, Neda
    Bastanfard, Azam
    2020 6TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2020,
12345