Deep Learning for Astrophysics, Understanding the Impact of Attention on Variability Induced by Parameter Initialization - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Deep Learning for Astrophysics, Understanding the Impact of Attention on Variability Induced by Parameter Initialization

Abstract

In the astrophysics domain, the detection and description of gamma rays is a research direction for our understanding of the universe. Gamma-ray reconstruction from Cherenkov telescope data is multi-task by nature. The image recorded in the Cherenkov camera pixels relates to the type, energy, incoming direction and distance of a particle from a telescope observation. We propose γ-PhysNet, a physically inspired multi-task deep neural network for gamma/proton particle classification, and gamma energy and direction reconstruction. As ground truth does not exist for real data, γ-PhysNet is trained and evaluated on large-scale Monte Carlo simulations. Robustness is then crucial for the transfer of the performance to real data. Relying on a visual explanation method, we evaluate the influence of attention on the variability due to weight initialization, and how it helps improve the robustness of the model. All the experiments are conducted in the context of single telescope analysis for the Cherenkov Telescope Array simulated data analysis.
Fichier principal
Vignette du fichier
2020_Jacquemont_icpr_explain_final.pdf (3.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03043058 , version 1 (07-12-2020)

Identifiers

  • HAL Id : hal-03043058 , version 1

Cite

Mikaël Jacquemont, Thomas Vuillaume, A Benoit, Gilles Maurin, Patrick Lambert. Deep Learning for Astrophysics, Understanding the Impact of Attention on Variability Induced by Parameter Initialization. ICPR'2020 Workshop Explainable Deep Learning-AI, Jan 2021, Milan (on line), Italy. ⟨hal-03043058⟩
199 View
179 Download

Share

Gmail Facebook X LinkedIn More