no code implementations • 18 Dec 2019 • Marc-Andre Schulz, Matt Chapman-Rounds, Manisha Verma, Danilo Bzdok, Konstantinos Georgatzis
The distribution of instances in the explanation space of our diagnostic classifier amplifies the different reasons for belonging to the same class - resulting in a representation that is uniquely useful for discovering latent subtypes.
no code implementations • 2 Dec 2019 • Matt Chapman-Rounds, Marc-Andre Schulz, Erik Pazos, Konstantinos Georgatzis
Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations.