On-manifold projected gradient descent

On-manifold projected gradient descent

This study provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with non-linear projections from input space onto these class manifolds. The tools are applied to the setting of neural network image c...

Full description

Bibliographic Details
Main Authors: Aaron Mahler, Tyrus Berry, Tom Stephens, Harbir Antil, Michael Merritt, Jeanie Schreiber, Ioannis Kevrekidis
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-02-01
Series:Frontiers in Computer Science
Subjects:
diffusion maps
kernel methods
manifold learning
Nyström approximation
adversarial attack
image classification
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2024.1274181/full

Internet

https://www.frontiersin.org/articles/10.3389/fcomp.2024.1274181/full

Similar Items