深度学习批归一化及其相关算法研究进展

刘建伟, 赵会丹, 罗雄麟, 许鋆 - 自动化学报, 2020 - aas.net.cn
neural network fields are summarized. And we sum up other methods to improve the training
performance of neural networkBayesian approximation: Representing model uncertainty in …

[PDF][PDF] 深度卷积神经网络的发展及其在计算机视觉领域的应用

张顺, 龚怡宏, 王进军 - 计算机学报, 2019 - cjc.ict.ac.cn
… convolutional neural networks, and briefly introduce MP neuron model, Hubel-Wiesel model
such as the L2 regularization, Dropout, Dropconnect and Maxout, several frequently-used …

[PDF][PDF] 基于正则化的函数连接神经网络研究及其复杂化工过程建模应用

贺彦林, 田业, 顾祥柏, 徐圆, 朱群雄 - 化工学报, 2020 - hgxb.cip.com.cn
learning speed of functional neural network is much improved. In order to verify the effectiveness
… Compensation of automatic weighing error of belt weigher based on BP neural network[…

无监督多重非局部融合的图像去噪方法

陈叶飞, 赵广社, 李国齐, 王鼎衡 - 自动化学报, 2022 - aas.net.cn
… His research interest covers deep learning, image recogition, big data, swarm intelligence, …
Table 6 Average PSNR (dB) and SSIM results of traditional and deep learning methods on …