Page 70 - 《应用声学）》2023年第5期

962 2023 年 9 月

[10] Le Cun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, tive adversarial networks[EB/OL]. arXiv Preprint, arXiv:
2015, 521(7553): 436–444. 1406.2661, 2014.
[11] Schmidhuber J. Deep learning in neural networks: an [16] 康旭, 张晓峰. 基于生成对抗神经网络的雷达遥感数据增广方
overview[J]. Neural Networks, 2015, 61: 85–117. 法 [J]. 系统仿真学报, 2022, 34(4): 920–927.
[12] Murphy J. An overview of convolutional neural network Kang Xu, Zhang Xiaofeng. Radar remote sensing data
architectures for deep learning[J]. Microway Inc, 2016: augmentation method based on generative adversarial
1–22. network[J]. Journal of System Simulation, 2022, 34(4):
[13] 高留刚, 李春迎, 陆正大, 等. 基于卷积神经网络生成虚拟平 920–927.
扫 CT 图像 [J]. 中国医学影像技术, 2022, 38(3): 440–444. [17] 邱根, 王锂, 白利兵. 基于生成对抗网络数据扩充的缺陷识别
Gao Liugang, Li Chunying, Lu Zhengda, et al. Generation 方法 [J]. 电子测量与仪器学报, 2021, 35(2): 212–220.
of virtual plain CT images based on convolutional neural Qiu Gen, Wang Li, Bai Libing. GANs-based synthetic
network[J]. Chinese Journal of Medical Imaging Technol- data augmentation for defects recognition[J]. Journal
ogy, 2022, 38(3): 440–444. of Electronic Measurement and Instrumentation, 2021,
[14] 徐卫鹏, 徐冰. 基于卷积神经网络的轴承故障诊断研究 [J]. 山 35(2): 212–220.
东科技大学学报 (自然科学版), 2021, 40(6): 121–128. [18] Shamshirband S, Mohammadi K, Khorasanizadeh H, et
Xu Weipeng, Xu Bing. Study on bearing fault diagnosis al. Estimating the diffuse solar radiation using a cou-
based on convolution neural network[J]. Journal of Shan- pled support vector machine–wavelet transform model[J].
dong University of Science and Technology(Natural Sci- Renewable and Sustainable Energy Reviews, 2016, 56:
ence), 2021, 40(6): 121–128. 428–435.
[15] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Genera-