Speaker
Tae Min Hong
(University of Pittsburgh (US))
Description
We present a novel implementation of classification using boosted decision trees (BDT) on field programmable gate arrays (FPGA). The firmware implementation of binary classification requiring 100 training trees with a maximum depth of 4 using four input variables gives a latency value of about 10ns. Two problems are presented, in the separation of electrons vs. photons and in the selection of vector boson fusion-produced Higgs bosons vs. the rejection of the multijet processes. Implementations such as these enable the level-1 trigger systems to be more sensitive to new physics at high energy experiments. The work is described in [2104.03408].
Primary authors
Tae Min Hong
(University of Pittsburgh (US))
Ben Carlson
(University of Pittsburgh)
Stephen Thomas Roche
(University of Pittsburgh (US))
