BriefGPT.xyz
May, 2019
紧致黎曼流形上的几何小波散射网络
Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds
HTML
PDF
Michael Perlmutter, Feng Gao, Guy Wolf, Matthew Hirn
TL;DR
本文介绍了一种基于仿射不变性和微分同胚稳定性的Geometric Scattering Transform方法，可以使卷积神经网络在流形和图结构领域中更具有普适性和稳定性。
Abstract
The
euclidean scattering transform
was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in
geometric deep learning
, which aims
→