A robust estimator of mutual information for deep learning interpretability

We develop the use of mutual information (MI), a well-established metric in information theory, to interpret the inner workings of deep learning (DL) models. To accurately estimate MI from a finite number of samples, we present GMM-MI (pronounced ‘Jimmie’), an algorithm based on Gaussian mixture mod...

Descripció completa

Dades bibliogràfiques

Autors principals:	Davide Piras, Hiranya V Peiris, Andrew Pontzen, Luisa Lucie-Smith, Ningyuan Guo, Brian Nord
Format:	Artigo
Idioma:	Inglês
Publicat:	IOP Publishing 2023-01-01
Col·lecció:	Machine Learning: Science and Technology
Matèries:	deep learning mutual information interpretability representation learning
Accés en línia:	https://doi.org/10.1088/2632-2153/acc444
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!