Convolutional spectral kernel learning with generalization guarantees
Authors:
- Jian LiJLJian Li
- Yong LiuYLYong Liu
- Weiping WangWWWeiping Wang
- 3 October 2022
- journal article
- research article
- Published by Elsevier in Artificial Intelligence
- Vol. 313
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62076234, 62106257)
- Chinese Academy of Sciences
This publication has 9 references indexed in Scilit:
- Theory of deep convolutional neural networks: DownsamplingNeural Networks, 2020
- Universality of deep convolutional neural networksApplied and Computational Harmonic Analysis, 2020
- Approximate Kernel Selection via Matrix ApproximationIEEE Transactions on Neural Networks and Learning Systems, 2020
- A Mathematical Theory of Deep Convolutional Neural Networks for Feature ExtractionIEEE Transactions on Information Theory, 2017
- Local Rademacher Complexity: Sharper risk bounds with and without unlabeled samplesNeural Networks, 2015
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012
- Local Rademacher complexitiesThe Annals of Statistics, 2005
- Rademacher penalties and structural risk minimizationIEEE Transactions on Information Theory, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998