3 citations · 3 across the 1 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors
Tobias Weber, Carla Sagebiel, Philipp Hennig
Physics-informed Gaussian processes (GPs) provide a principled framework for scientific inference by expressing uncertainty over empirical measurements, boundary conditions, and go…
cs.LG2022★ 3 cited
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Jan-Philipp Schulze, Philip Sperl, Ana Răduţoiu +2
Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss. Samples unlike the ones seen during training cause a…