其实,这篇文章的摘要很好地总结了整体的思路。一共四句话,非常简明扼要。
我们首先来翻译一下论文的摘要:
第一句:This paper develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy.
翻译:本文提出了新的深度学习方法,即深度残差收缩网络,来提高深度学习算法从强噪声信号中学习特征的能力,并且取得较高的故障诊断准确率。
解释:不仅明确了所提出的方法(深度残差收缩网络),而且指出了面向的信号类型(强噪声信号)。
第二句:Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features.
翻译:软阈值化作为非线性层,嵌入到深度神经网络之中,以消除不重要的特征。
解释:深度残差收缩网络是ResNet的改进。这里解释了深度残差收缩网络与ResNet的第一点不同之处——引入了软阈值化。
第三句:Moreover, considering that it is generally challenging to set proper values for the thresholds, the developed deep residual shrinkage networks integrate a few specialized neural networks as trainable modules to automatically determine the thresholds, so that professional expertise on signal processing is not required.
翻译:更进一步地,考虑到软阈值化中的阈值是难以设定的,本文所提出的深度残差收缩网络,采用了一个子网络,来自动地设置这些阈值,从而避免了信号处理领域的专业知识。
解释:这句话点明了本文的核心贡献。本文不仅在网络模型中引入了软阈值化,而且给出了自动设置阈值的方式。
第四句:The efficacy of the developed methods is validated through experiments with various types of noise.
翻译:该方法的有效性通过不同噪声下的实验得到了验证。
解释:实验验证部分考虑了不同种类噪声的影响。
总结:深度残差收缩网络=ResNet+软阈值化+自动设置阈值。
转载网址:
深度残差收缩网络:(一)背景知识 https://www.cnblogs.com/yc-9527/p/11598844.html
深度残差收缩网络:(二)整体思路 https://www.cnblogs.com/yc-9527/p/11601322.html
深度残差收缩网络:(三)网络结构 https://www.cnblogs.com/yc-9527/p/11603320.html
深度残差收缩网络:(四)注意力机制下的阈值设置 https://www.cnblogs.com/yc-9527/p/11604082.html
深度残差收缩网络:(五)实验验证 https://www.cnblogs.com/yc-9527/p/11610073.html
论文网址:
M. Zhao, S. Zhong, X. Fu, B. Tang, and M. Pecht, “Deep Residual Shrinkage Networks for Fault Diagnosis,” IEEE Transactions on Industrial Informatics, 2019, DOI: 10.1109/TII.2019.2943898
https://ieeexplore.ieee.org/document/8850096