no code implementations • 21 Mar 2024 • Laura O'Mahony, David JP O'Sullivan, Nikola S. Nikolov
Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions.
1 code implementation • 19 Apr 2023 • Laura O'Mahony, Vincent Andrearczyk, Henning Muller, Mara Graziani
Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units.