Interpretable convolutional neural networks via feedforward design
Authors:
- C.-C. Jay KuoCKC.-C. Jay Kuo
- Min ZhangMZMin Zhang
- Siyang LiSLSiyang Li
- Jiali DuanJDJiali Duan
- Yueru ChenYCYueru Chen
- 1 April 2019
- journal article
- research article
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 60, 346-359
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Air Force Research Laboratory (FA8750-16-2-0173)
- Defense Advanced Research Projects Agency
This publication has 14 references indexed in Scilit:
- Understanding convolutional neural networks via discriminant feature analysisAPSIPA Transactions on Signal and Information Processing, 2018
- On data-driven Saak transformJournal of Visual Communication and Image Representation, 2018
- The CNN as a Guided Multilayer RECOS Transform [Lecture Notes]IEEE Signal Processing Magazine, 2017
- Understanding convolutional neural networks with a mathematical modelJournal of Visual Communication and Image Representation, 2016
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012
- High dimensional covariance matrix estimation using a factor modelJournal of Econometrics, 2008
- Hierarchical models of object recognition in cortexNature Neuroscience, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989