Adrian Deutscher-Bishop
Use of Conditional Normalizing Flows in Background Modeling
Detecting a specific event from a particle accelerator requires having a model of the background of that event. Usually, this is done using Monte Carlo simulations of events, but these can be inaccurate. This summer, I will continue my research into Conditional Normalizing Flows, which are a type of neural network which transforms Monte Carlo simulations of events into backgrounds that more resemble the actual data.
Message To Sponsor
Thank you so much for allowing me to continue my particle physics research this summer! I really feel like this experience has set me up for success in both graduate school and for my planned future career doing particle physics research. I have not only learned what the day-to-day of particle physics research involves and what sorts of analysis techniques are used, but that I really enjoy doing particle physics research.
Major: Physics
Mentor: Haichen Wang, Physics
Sponsor: Anselm MPS Fund