Transformers trained on cosmic ray simulations learn physically plausible features in positional encodings for symmetric air showers and in attention mechanisms for galaxy-origin particles.
Deep-learning based reconstruction of the shower maxi- mum Xmax using the water-Cherenkov detectors of the Pierre Auger Observa- tory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
What exactly did the Transformer learn from our physics data?
Transformers trained on cosmic ray simulations learn physically plausible features in positional encodings for symmetric air showers and in attention mechanisms for galaxy-origin particles.