196 citations · 243 across the 10 of their papers we have counts for
6 papers · 1 filter
Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
Ling Han, Hao Huang, Dustin Scheinost +2
Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated informati…
Conformal Autoregressive Generation: Beam Search with Coverage Guarantees
Nicolas Deutschmann, Marvin Alberts, María Rodríguez Martínez
We introduce two new extensions to the beam search algorithm based on conformal predictions (CP) to produce sets of sequences with theoretical coverage guarantees. The first method…
Is Attention Interpretation? A Quantitative Assessment On Sets
Jonathan Haab, Nicolas Deutschmann, Maria Rodríguez Martínez
The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-comp…
Learning Invariances for Interpretability using Supervised VAE
An-phi Nguyen, María Rodríguez Martínez
We propose to learn model invariances as a means of interpreting a model. This is motivated by a reverse engineering principle. If we understand a problem, we may introduce inducti…
On quantitative aspects of model interpretability
An-phi Nguyen, María Rodríguez Martínez
Despite the growing body of work in interpretable machine learning, it remains unclear how to evaluate different explainability methods without resorting to qualitative assessment…
DeStress: Deep Learning for Unsupervised Identification of Mental Stress in Firefighters from Heart-rate Variability (HRV) Data
Ali Oskooei, Sophie Mai Chau, Jonas Weiss +3
In this work we perform a study of various unsupervised methods to identify mental stress in firefighter trainees based on unlabeled heart rate variability data. We collect RR inte…