Deep learning

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

Interpretable Machine Learning

Creating an interface between machine learning models and human beings.

Interpretable Machine Learning