The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
Open accessAbstract
Deep convolutional neural networks (DCNNs) have led to breakthrough results in numerous practical machine learning tasks, such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction and then feed the results thereof into a classifier. The mathematical analysis of DCNNs for feature extraction was initiated by Mallat, 2012. Specifically, Mallat considered so-called scattering networks based on a wavelet transform followed by the modulus non-linearity in each network layer, and proved translation invariance (asymptotically in the wavelet scale parameter) and deformation stability of the corresponding feature extractor. This paper complements Mallat's results by developing a theory that encompasses general convolutional transforms, or in more technical parlance, general semi-discrete frames (including Weyl-Heisenberg filters, curvelets, shearlets, ridgelets, wavelets, and learned filters), general Lipschitz-continuous non-linearities (e.g., rectified linear units, shifted logistic sigmoids, hyperbolic tangents, and modulus functions), and general Lipschitz-continuous pooling operators emulating, e.g., sub-sampling and averaging. In addition, all of these elements can be different in different network layers. For the resulting feature extractor, we prove a translation invariance result of vertical nature in the sense of the features becoming progressively more translation-invariant with increasing network depth, and we establish deformation sensitivity bounds that apply to signal classes such as, e.g., band-limited functions, cartoon functions, and Lipschitz functions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
A Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Daubechies, I. (1992) · doi:10.1137/1.9781611970104 · Cited by 15,979
Daubechies, I., & Heil, C. (1992) · Computers in Physics · doi:10.1063/1.4823127 · Cited by 15,631
Rudin, W. (1973) · Cited by 13,740
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Garreau, G. A., & Rudin, W. (1987) · The Statistician · doi:10.2307/2348852 · Cited by 10,622
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
The contourlet transform: an efficient directional multiresolution image representation
Do, M. N., & Vetterli, M. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859376 · Cited by 3,952
(1989) · neural information processing systems · Cited by 3,736
Orthogonal least squares learning algorithm for radial basis function networks
Chen, S., Cowan, C. F. N., & Grant, P. M. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.80341 · Cited by 3,362
Characterization of signals from multiscale edges
Mallat, S., & Zhong, S. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.142909 · Cited by 3,200
Foundations of Time-Frequency Analysis
Gröchenig, K. (2001) · Applied and Numerical Harmonic Analysis · doi:10.1007/978-1-4612-0003-1 · Cited by 2,923
Musical genre classification of audio signals
Tzanetakis, G., & Cook, P. (2002) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/tsa.2002.800560 · Cited by 2,798
A Wavelet Tour of Signal Processing : The Sparse Way
Mallat, S., & Gabriel Peyré, A. (2008) · Cited by 2,734
The dual-tree complex wavelet transform
Selesnick, I. W., Baraniuk, R. G., & Kingsbury, N. C. (2005) · IEEE Signal Processing Magazine · doi:10.1109/msp.2005.1550194 · Cited by 2,475
Convolutional networks and applications in vision
LeCun, Y., Kavukcuoglu, K., & Farabet, C. (2010) · Proceedings of 2010 IEEE International Symposium on Circuits and Systems · doi:10.1109/iscas.2010.5537907 · Cited by 2,213
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Acoustic Modeling Using Deep Belief Networks
Mohamed, A.-R., Dahl, G. E., & Hinton, G. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2109382 · Cited by 1,727
Invariant Scattering Convolution Networks
Bruna, J., & Mallat, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.230 · Cited by 1,633
Image representation using 2D Gabor wavelets
Lee, T. S. (1996) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.541406 · Cited by 1,629
New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities
Candès, E. J., & Donoho, D. L. (2004) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.10116 · Cited by 1,545
DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
Tola, E., Lepetit, V., & Fua, P. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.77 · Cited by 1,405
Texture classification and segmentation using wavelet frames
Unser, M. (1995) · IEEE Transactions on Image Processing · doi:10.1109/83.469936 · Cited by 1,329
Grafakos, L. (2008) · Graduate Texts in Mathematics · doi:10.1007/978-0-387-09432-8 · Cited by 1,324
Painless nonorthogonal expansions
Daubechies, I., Grossmann, A., & Meyer, Y. (1986) · Journal of Mathematical Physics · doi:10.1063/1.527388 · Cited by 1,290
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383157 · Cited by 1,086
Kaiser, G. (2011) · Birkhäuser Boston eBooks · doi:10.1007/978-0-8176-8111-1 · Cited by 1,078
Mallat, S. (2012) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.21413 · Cited by 1,038
Ridgelets: a key to higher-dimensional intermittency?
Candès, E. J., & Donoho, D. L. (1999) · Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.1999.0444 · Cited by 893
FEATURE EXTRACTION BASED ON MORLET WAVELET AND ITS APPLICATION FOR MECHANICAL FAULT DIAGNOSIS
LIN, J., & QU, L. (2000) · Journal of Sound and Vibration · doi:10.1006/jsvi.2000.2864 · Cited by 879
Littlewood-Paley Theory and the Study of Function Spaces
Frazier, M., Jawerth, B., & Weiss, G. (1991) · CBMS Regional Conference Series in Mathematics · doi:10.1090/cbms/079 · Cited by 831
Object Recognition with Features Inspired by Visual Cortex
Serre, T., Wolf, L., & Poggio, T. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.254 · Cited by 821
Linear Operator Theory in Engineering and Science
Naylor, A. W., & Sell, G. R. (1982) · Applied Mathematical Sciences · doi:10.1007/978-1-4612-5773-8 · Cited by 787
Anden, J., & Mallat, S. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2326991 · Cited by 666
Why is Real-World Visual Object Recognition Hard?
Pinto, N., Cox, D. D., & DiCarlo, J. J. (2008) · PLoS Computational Biology · doi:10.1371/journal.pcbi.0040027 · Cited by 537
Ma, J., & Plonka, G. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2009.935453 · Cited by 464
Multiclass Object Recognition with Sparse, Localized Features
Mutch, J., & Lowe, D. G. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.200 · Cited by 453
Frames and Stable Bases for Shift-Invariant Subspaces of L2(ℝd)
Ron, A., & Shen, Z. (1995) · Canadian Journal of Mathematics · doi:10.4153/cjm-1995-056-1 · Cited by 348
Frame-theoretic analysis of oversampled filter banks
Bolcskei, H., Hlawatsch, F., & Feichtinger, H. G. (1998) · IEEE Transactions on Signal Processing · doi:10.1109/78.735301 · Cited by 318
Self-citationLarge-scale Learning with SVM and Convolutional for Generic Object Categorization
Huang, F. J., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.164 · Cited by 308
Rigid-Motion Scattering for Texture Classification
Sifre, L., & Mallat, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.1687 · Cited by 272
Duality and Biorthogonality for Weyl-Heisenberg Frames
Janssen, A. J. E. M. (1994) · Journal of Fourier Analysis and Applications · doi:10.1007/s00041-001-4017-4 · Cited by 268
Candès, E. J., & Donoho, D. L. (2005) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2005.02.004 · Cited by 258
Sparse Components of Images and Optimal Atomic Decompositions
Donoho, D. L. (2001) · Constructive Approximation · doi:10.1007/s003650010032 · Cited by 230
Deep roto-translation scattering for object classification
Oyallon, E., & Mallat, S. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298904 · Cited by 220
Gabor Time-Frequency Lattices and the Wexler-Raz Identity
Daubechies, I., Landau, H. J., & Landau, Z. (1994) · Journal of Fourier Analysis and Applications · doi:10.1007/s00041-001-4018-3 · Cited by 193
Shearlets: Multiscale Analysis for Multivariate Data
Kutyniok, G., & Demetrio Labate, A. (2012) · International Linear Collider · doi:10.1007/978-0-8176-8316-0 · Cited by 191
Dettori, L., & Semler, L. (2007) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2006.08.002 · Cited by 170
Lee, C.-H., Shih, J.-L., Yu, K.-M., et al. (2009) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2009.2017635 · Cited by 148
Analysis of time-frequency scattering transforms
Czaja, W., & Li, W. (2017) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2017.08.005 · Cited by 55
Directional dyadic wavelet transforms: design and algorithms
Vandergheynst, P., & Gobbers, J.-F. (2002) · IEEE Transactions on Image Processing · doi:10.1109/tip.2002.999670 · Cited by 44
Deep convolutional neural networks based on semi-discrete frames
Wiatowski, T., & Bölcskei, H. (2015) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2015.7282648 · Cited by 30
Self-citationEnergy Propagation in Deep Convolutional Neural Networks
Wiatowski, T., Grohs, P., & Bölcskei, H. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2756880 · Cited by 26
Self-citationRidgelet-type Frame Decompositions for Sobolev Spaces related to Linear Transport
Grohs, P. (2011) · Journal of Fourier Analysis and Applications · doi:10.1007/s00041-011-9206-1 · Cited by 20
Deep convolutional neural networks on cartoon functions
Grohs, P., Wiatowski, T., & Bölcskei, H. (2016) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2016.7541482 · Cited by 20
Self-citationDeep Roto-Translation Scattering for Object ClassificationPreprint
Oyallon, E., & Mallat, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.8659 · Cited by 7
Cited by
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Deep feature based rice leaf disease identification using support vector machine
Sethy, P. K., Barpanda, N. K., Rath, A. K., & Behera, S. K. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105527 · Cited by 598
Deep Learning in Mining Biological Data
Mahmud, M., Kaiser, M. S., McGinnity, T. M., & Hussain, A. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09773-x · Cited by 446
Optimal approximation of piecewise smooth functions using deep ReLU neural networks
Petersen, P., & Voigtlaender, F. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.08.019 · Cited by 432
Understanding convolutional neural networks with a mathematical model
Kuo, C.-C. J. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.11.003 · Cited by 414
Metadata
- Authors
- Wiatowski, T., & Bolcskei, H.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2018-03
- Volume
- 64
- Issue
- 3
- Pages
- 1845-1866
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W2196920785
- Cited by
- 399
- References
- 62
- FWCI
- 61.82
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.