Interpretability

Concept Activation Regions: A Generalized Framework For Concept-Based Explanations

We extend existing feature and example importance methods to unsupervised learning.

Jonathan Crabbé, Mihaela van der Schaar

Concept Activation Regions: A Generalized Framework For Concept-Based Explanations

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

We benchmark treatment effect models with interpretability tools.

Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar

Label-Free Explainability for Unsupervised Models

We extend existing feature and example importance methods to unsupervised learning.

Jonathan Crabbé, Mihaela van der Schaar

Label-Free Explainability for Unsupervised Models

DAUX: a Density-based Approach for Uncertainty eXplanations

We introduce DAUX, an interpretability framework to interpret model uncertainty.

Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat, Mihaela van der Schaar

Explaining Latent Representations with a Corpus of Examples

We introduce SimplEx, a case-based reasoning explanation method that permits to decompose latent representations with a corpus of example.

Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar

Explaining Latent Representations with a Corpus of Examples

Explaining Time Series Predictions with Dynamic Masks

We introduce Dynamask, a perturbation-based feature importance method to explain the predictions of time series models.

Jonathan Crabbé, Mihaela van der Schaar

Explaining Time Series Predictions with Dynamic Masks

Learning outside the black-box: the pursuit of interpretable models

We introduce Symbolic Pursuit, a new method for symbolic regression based on Meijer G-functions and the projection pursuit algorithm.

Jonathan Crabbé, Yao Zhang, William R. Zame, Mihaela van der Schaar

Explainable Artificial Intelligence

Creating an interface between machine learning models and human beings.

Explainable Artificial Intelligence