no code implementations • 11 Apr 2024 • Brian Bell, Michael Geyer, David Glickenstein, Keaton Hamm, Carlos Scheidegger, Amanda Fernandez, Juston Moore
This article proposes a new framework for studying adversarial examples that does not depend directly on the distance to the decision boundary.
no code implementations • 1 Aug 2023 • Brian Bell, Michael Geyer, David Glickenstein, Amanda Fernandez, Juston Moore
We explore the equivalence between neural networks and kernel methods by deriving the first exact representation of any finite-size parametric classification model trained with gradient descent as a kernel machine.