Extending the Physics Reach of LHCb in Run 3 Using Machine Learning in theReal-Time Data Ingestion and Reduction System [graphic]

Michael Sokoloff, Rui Fang, Henry Fredrick Schreiner, Marian Stahl, Constantin Weisser, Mike Williams
2020 Figshare  
This poster describes a hybrid machine learning algorithm for finding primary vertices in proton-proton collisions produced in the LHCb detector at CERN in Run 3. A proof-of-principle has been demonstrated using a kernel density estimator that transforms sparse 3D data into a rich 1D data set that is processed by a convolutional neural network. The algorithm learns target histograms that serve as proxies for the primary vertex positions. Basic concepts are illustrated. Results to date are
more » ... s to date are summarized. Plans for future work are presented.
doi:10.6084/m9.figshare.11803158.v3 fatcat:6nyvjwq7tnhgzeepbocevbgmpi