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...

Cijeli opis

Bibliografski detalji

Glavni autori:	Davide Piras, Hiranya V Peiris, Andrew Pontzen, Luisa Lucie-Smith, Ningyuan Guo, Brian Nord
Format:	Artigo
Jezik:	Inglês
Izdano:	IOP Publishing 2023-01-01
Serija:	Machine Learning: Science and Technology
Teme:	deep learning mutual information interpretability representation learning
Online pristup:	https://doi.org/10.1088/2632-2153/acc444
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!