Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment

About

A novel b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS Experiment. This talk presents the expected performance of the RNN based b-tagging in simulated $t \bar t$ events. The RNN based b-tagging processes properties of tracks associated to jets which are represented in sequences. In contrast to traditional impact-parameter-based b-tagging algorithms which assume the tracks of jets are independent from each other, RNN based b-tagging can exploit the spatial and kinematic correlations of tracks which are initiated from the same b-hadrons. The neural network nature of the tagging algorithm also allows the flexibility of extending input features to include more track properties than can be effectively used in traditional algorithms..

0:00:00 Slide 1

0:00:11 Slide 2

0:00:15 Slide 3

0:00:35 Slide 4

0:01:32 Slide 5

0:02:19 Slide 6

0:02:58 Slide 7

0:04:04 Slide 8

0:04:42 Slide 9

0:05:40 Slide 10

0:06:55 Slide 11