Picture for Grégoire Montavon

Grégoire Montavon

Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features

Add code
Aug 30, 2024
Viaarxiv icon

The Clever Hans Effect in Unsupervised Learning

Add code
Aug 15, 2024
Viaarxiv icon

MambaLRP: Explaining Selective State Space Sequence Models

Add code
Jun 11, 2024
Viaarxiv icon

XpertAI: uncovering model strategies for sub-manifolds

Add code
Mar 12, 2024
Viaarxiv icon

Explaining Predictive Uncertainty by Exposing Second-Order Effects

Add code
Jan 30, 2024
Viaarxiv icon

Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI

Add code
Oct 13, 2023
Viaarxiv icon

Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation

Add code
Oct 03, 2023
Viaarxiv icon

Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks

Add code
Apr 12, 2023
Viaarxiv icon

Explainable AI for Time Series via Virtual Inspection Layers

Add code
Mar 11, 2023
Viaarxiv icon

Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces

Add code
Dec 30, 2022
Viaarxiv icon