Deep Residual Learning and PDEs on Manifold
classification
💻 cs.IT
math.IT
keywords
equationdeeppdestransportcontrolmanifoldnetworkproblem
read the original abstract
In this paper, we formulate the deep residual network (ResNet) as a control problem of transport equation. In ResNet, the transport equation is solved along the characteristics. Based on this observation, deep neural network is closely related to the control problem of PDEs on manifold. We propose several models based on transport equation and Hamilton-Jacobi equation. The discretization of these PDEs on point cloud is also discussed.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning
Graph Laplacian interpolating activation replaces softmax in DNNs and improves natural accuracy, robust accuracy, and data efficiency.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.