Portal de Periódicos da CAPES

Deep-learning jets with uncertainties and more

2020; SciPost.org; Volume: 8; Issue: 1 Linguagem: Inglês

10.21468/scipostphys.8.1.006

2542-4653

S. Bollweg, Manuel Haußmann, Gregor Kasieczka, Michel Luchmann, Tilman Plehn, J. Thompson,

Computational Physics and Python Applications

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show how they capture statistical uncertainties from finite training samples, systematics related to the jet energy scale, and stability issues through pile-up. Altogether, Bayesian networks offer many new handles to understand and control deep learning at the LHC without introducing a visible prior effect and without compromising the network performance.