A robust estimator of mutual information for deep learning interpretability

1 code implementation • 31 Oct 2022 • Davide Piras, Hiranya V. Peiris, Andrew Pontzen, Luisa Lucie-Smith, Ningyuan Guo, Brian Nord

We develop the use of mutual information (MI), a well-established metric in information theory, to interpret the inner workings of deep learning models.

Disentanglement