Speaker
Prof.
Martin Sevior
(University of Melbourne)
Description
Data from B-physics experiments at the KEKB collider have a substantial background from $e^{+}e^{-}\to q \bar{q}$ events. To suppress this we employ deep neural network algorithms. These provide improved signal from background discrimination. However, the neural network develops a substantial correlation with the $\Delta E$ kinematic variable used to distinguish signal from background in the final fit due to its relationship with the input variables. The effect of this correlation is counter-acted by deploying an adversarial neural network. Overall the adversarial deep neural network performs better than an unoptimised commercial package, NeuroBayes.
Authors
Mr
Anton Hawthorne-Gonzalvez
(University of Melbourne)
Prof.
Martin Sevior
(University of Melbourne)
