181 citations · 377 across the 22 of their papers we have counts for
3 papers · 1 filter
A robust estimator of mutual information for deep learning interpretability
Davide Piras, Hiranya V. Peiris, Andrew Pontzen +3
We develop the use of mutual information (MI), a well-established metric in information theory, to interpret the inner workings of deep learning models. To accurately estimate MI f…
Fast and realistic large-scale structure from machine-learning-augmented random field simulations
Davide Piras, Benjamin Joachimi, Francisco Villaescusa-Navarro
Producing thousands of simulations of the dark matter distribution in the Universe with increasing precision is a challenging but critical task to facilitate the exploitation of cu…
Discovering the building blocks of dark matter halo density profiles with neural networks
Luisa Lucie-Smith, Hiranya V. Peiris, Andrew Pontzen +3
The density profiles of dark matter halos are typically modeled using empirical formulae fitted to the density profiles of relaxed halo populations. We present a neural network mod…