Picture for Christophe Marsala

Christophe Marsala

A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text

Add code
May 16, 2024
Viaarxiv icon

Dynamic Interpretability for Model Comparison via Decision Rules

Add code
Sep 29, 2023
Viaarxiv icon

Achieving Diversity in Counterfactual Explanations: a Review and Discussion

Add code
May 10, 2023
Viaarxiv icon

Integrating Prior Knowledge in Post-hoc Explanations

Add code
Apr 25, 2022
Figure 1 for Integrating Prior Knowledge in Post-hoc Explanations
Figure 2 for Integrating Prior Knowledge in Post-hoc Explanations
Figure 3 for Integrating Prior Knowledge in Post-hoc Explanations
Figure 4 for Integrating Prior Knowledge in Post-hoc Explanations
Viaarxiv icon

The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations

Add code
Jul 22, 2019
Figure 1 for The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations
Figure 2 for The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations
Figure 3 for The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations
Figure 4 for The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations
Viaarxiv icon

Issues with post-hoc counterfactual explanations: a discussion

Add code
Jun 11, 2019
Figure 1 for Issues with post-hoc counterfactual explanations: a discussion
Figure 2 for Issues with post-hoc counterfactual explanations: a discussion
Figure 3 for Issues with post-hoc counterfactual explanations: a discussion
Figure 4 for Issues with post-hoc counterfactual explanations: a discussion
Viaarxiv icon

Detecting Potential Local Adversarial Examples for Human-Interpretable Defense

Add code
Sep 07, 2018
Figure 1 for Detecting Potential Local Adversarial Examples for Human-Interpretable Defense
Figure 2 for Detecting Potential Local Adversarial Examples for Human-Interpretable Defense
Viaarxiv icon

Defining Locality for Surrogates in Post-hoc Interpretablity

Add code
Jun 19, 2018
Figure 1 for Defining Locality for Surrogates in Post-hoc Interpretablity
Figure 2 for Defining Locality for Surrogates in Post-hoc Interpretablity
Figure 3 for Defining Locality for Surrogates in Post-hoc Interpretablity
Figure 4 for Defining Locality for Surrogates in Post-hoc Interpretablity
Viaarxiv icon

Inverse Classification for Comparison-based Interpretability in Machine Learning

Add code
Dec 22, 2017
Figure 1 for Inverse Classification for Comparison-based Interpretability in Machine Learning
Figure 2 for Inverse Classification for Comparison-based Interpretability in Machine Learning
Figure 3 for Inverse Classification for Comparison-based Interpretability in Machine Learning
Figure 4 for Inverse Classification for Comparison-based Interpretability in Machine Learning
Viaarxiv icon