Speaker
Ms
Fernanda Psihas
(Indiana University)
Description
A premier challenge of HEP analysis is the interpretation of highly multivariate data. The efforts to extract the strongest measurements from the available data combined with access to large-scale computing resources allow researchers to take advantage of and contribute to the development of cutting-edge machine learning tools. Recent applications have shown that some techniques, especially deep learning, significantly improve the physics reach of running neutrino experiments. A variety of applications are under development using these tools not only for analysis but for reconstruction and even simulation.
The Fermilab Machine Learning Working Group brings together a community of scientists from across the laboratory with an interest in machine learning. This presentation will summarize the most prominent machine learning applications in use in Fermilab experiments and introduce the activities of the Working Group.
Primary author
Ms
Fernanda Psihas
(Indiana University)
Co-authors
Dr
Alexander Himmel
(Fermilab)
Dr
Alexander Radovic
(College of William and Mary)
Ms
Auralee Edelen
(Fermilab, CSU)
Dr
Brian Nord
(Fermilab)
Dr
Gabriel Perdue
(Fermilab)