Transcription of High-Frequency Component Helps Explain the Generalization ...
{{id}} {{{paragraph}}}
Example: quiz answers
High-Frequency Component Helps Explain the Generalization ...
High-Frequency Component Helps Explainthe Generalization of Convolutional Neural NetworksHaohan Wang, Xindi Wu, Zeyi Huang, Eric P. XingSchool of Computer ScienceCarnegie Mellon investigate the relationship between the frequencyspectrum of image data and the Generalization behaviorof convolutional neural networks (CNN). We first noticeCNN s ability in capturing the High-Frequency componentsof images. These High-Frequency components are almost im-perceptible to a human. Thus the observation leads to multi-ple hypotheses that are related to the Generalization behav-iors of CNN, including a potential explanation for adver-sarial examples, a discussion of CNN s trade-off betweenrobustness and accuracy, and some evidence in understand-ing training IntroductionDeep learning has achieved many
progressively, including studying the properties of stochas-tic gradient descent [31], different complexity measures [46], generalization gaps [50], and many more from differ-ent model or algorithm perspectives [30, 43, 7, 51]. In this paper, inspired by previous understandings that convolutional neural networks (CNN) can learn from con-
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: