On Generalizations of the Nonwindowed Scattering Transform.

On Generalizations of the Nonwindowed Scattering Transform.
复制标题

关于无窗散射变换的推广。

DOI:
10.1016/j.acha.2023.101597
复制
发表时间:
2024
影响因子:
2.5
通讯作者:
Little,Anna
Little,Anna
中科院分区:
数学1区
文献类型:
--
作者:
Chua,Albert;Hirn,Matthew;Little,Anna

文献摘要

参考文献

相似文献

在本文中,我们推广有限深度小波散射变换,我们制定为L q(R n)规范的级联连续小波变换(或二进小波变换)和收缩非线性。然后,我们提供这些运营商的规范,证明这些运营商是定义良好的,并Lipschitz连续的行动的C2同构在特定情况下。最后,我们推广了我们的结果,构造了一个对R∈ SO(n)的旋转作用不变性的算子和一个对R∈ SO(n)的旋转作用等变的算子。
In this paper, we generalize finite depth wavelet scattering transforms, which we formulate as L q (R n) norms of a cascade of continuous wavelet transforms (or dyadic wavelet transforms) and contractive nonlinearities. We then provide norms for these operators, prove that these operators are well-defined, and are Lipschitz continuous to the action of C 2 diffeomorphisms in specific cases. Lastly, we extend our results to formulate an operator invariant to the action of rotations R∈ SO (n) and an operator that is equivariant to the action of rotations of R∈ SO (n).
DOI: 10.1016/j.acha.2017.08.005
发表时间: 2016
影响因子: 2.5
作者:
W. Czaja;Weilin Li
通讯作者: Weilin Li
具有最小规律性的变形的散射变换的稳定性
DOI: 10.48550/arxiv.2205.11142
发表时间: 2022
期刊: ArXiv
影响因子: --
作者:
F. Nicola;S. I. Trapasso
通讯作者: S. I. Trapasso
Sobolev 空间上深度卷积神经网络的变形稳定性
DOI: 10.1109/icassp.2018.8462158
发表时间: 2018
期刊: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
M. Koller;Johannes Grobmann;U. Mönich;H. Boche
通讯作者: H. Boche
DOI: --
发表时间: 2019-05
期刊: Proceedings of machine learning research
影响因子: --
作者:
Michael Perlmutter;Feng Gao;Guy Wolf;M. Hirn
通讯作者: Michael Perlmutter;Feng Gao;Guy Wolf;M. Hirn