×

zbMATH — the first resource for mathematics

Kymatio: scattering transforms in Python. (English) Zbl 07255091
Summary: The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks, including PyTorch and TensorFlow/Keras. The transforms are implemented on both CPUs and GPUs, the latter offering a significant speedup over the former. The package also has a small memory footprint. Source code, documentation, and examples are available under a BSD license at https://www.kymat.io.
MSC:
68T05 Learning and adaptive systems in artificial intelligence
PDF BibTeX XML Cite
Full Text: Link
References:
[1] T. Adel, T. Cohen, M. Caan, M. Welling, et al. 3D scattering transforms for disease classification in neuroimaging.NeuroImage: Clinical, 14:506-517, 2017. doi: 10.1016/j. nicl.2017.02.004.
[2] J. And´en et al. Scatnet.Computer Software, 2014. URLhttp://www.di.ens.fr/data/ software/scatnet.
[3] J. And´en and S. Mallat. Deep scattering spectrum.IEEE Trans. Signal Process., 62(16): 4114-4128, Aug 2014. doi: 10.1109/TSP.2014.2326991. · Zbl 1394.94040
[4] T. Angles and S. Mallat. Generative networks as inverse problems with scattering transforms. InProc. ICLR, 2018.
[5] J. Bruna and S. Mallat. Invariant scattering convolution networks.IEEE Trans. Pattern Anal. Mach. Intell., 35(8):1872-1886, 2013. doi: 10.1109/TPAMI.2012.230.
[6] J. Bruna, S. Mallat, E. Bacry, and J.-F. Muzy. Intermittent process analysis with scattering moments.Ann. Statist., 43(1):323-351, 02 2015. doi: 10.1214/14-AOS1276. · Zbl 1308.62168
[7] V. Chud´aˇcek et al. Scattering transform for intrapartum fetal heart rate variability fractal analysis: A case-control study.IEEE Trans. Biomed. Eng., 61(4):1100-1108, 2014. doi: 10.1109/TBME.2013.2294324.
[8] M. Eickenberg et al. Solid harmonic wavelet scattering: Predicting quantum molecular energy from invariant descriptors of 3D electronic densities. InProc. NIPS, pages 6540-6549, 2017.
[9] M. Eickenberg et al. Solid harmonic wavelet scattering for predictions of molecule properties. The Journal of Chemical Physics, 148(24):241732, 2018. doi: 10.1063/1.5023798.
[10] V. Lostanlen and S. Mallat. Wavelet scattering on the pitch spiral. InProc. DAFx, 2015. 5
[11] S. Mallat. Group invariant scattering.Comm. Pure Appl. Math., 65(10):1331-1398, 2012. doi: 10.1002/cpa.21413. · Zbl 1282.47009
[12] E. Oyallon and S. Mallat. Deep roto-translation scattering for object classification. InProc. CVPR, June 2015.
[13] E. Oyallon et al. Scattering networks for hybrid representation learning.IEEE Trans. Pattern Anal. Mach. Intell., 41(9):2208-2221, 2018. doi: 10.1109/TPAMI.2018.2855738.
[14] F. Pedregosa et al. Scikit-learn: Machine learning in Python.J. Mach. Learn. Res., 12(Oct): 2825-2830, 2011. · Zbl 1280.68189
[15] T. N. Sainath et al. Deep scattering spectra with deep neural networks for LVCSR tasks. In Proc. Interspeech, 2014.
[16] L. Sifre and S. Mallat. Rotation, scaling and deformation invariant scattering for texture discrimination. InProc. CVPR, 2013. doi: 10.1109/CVPR.2013.163.
[17] I. Waldspurger. Exponential decay of scattering coefficients. InProc. SampTA, pages 143-146, 2017. doi: 10.1109/SAMPTA.2017.8024473.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.