A robust estimator of mutual information for deep learning interpretability

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...

Full description

Bibliographic Details
Main Authors: Davide Piras, Hiranya V Peiris, Andrew Pontzen, Luisa Lucie-Smith, Ningyuan Guo, Brian Nord
Format: Article
Language:English
Published: IOP Publishing 2023-01-01
Series:Machine Learning: Science and Technology
Subjects:
deep learning
mutual information
interpretability
representation learning
Online Access:https://doi.org/10.1088/2632-2153/acc444

Internet

https://doi.org/10.1088/2632-2153/acc444

Similar Items