Jonathan Crabbé
Jonathan Crabbé
Home
Posts
Projects
Talks
Publications
Contact
CV
Light
Dark
Automatic
Deep learning
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
PDF
Cite
Code
Project
Project
Label-Free Explainability for Unsupervised Models
We extend existing feature and example importance methods to unsupervised learning.
Jonathan Crabbé
,
Mihaela van der Schaar
PDF
Cite
Code
Project
Project
Video
Representation Learning
Learning realistic representations of the world.
Robust Machine Learning
Making sure that machines are doing what they are supposed to do.
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
PDF
Cite
Code
Project
Video
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
PDF
Cite
Code
Project
Video
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
PDF
Cite
Code
Project
Video
Explainable Artificial Intelligence
Creating an interface between machine learning models and human beings.
Cite
×