Machine learning in high energy physics: a conversation over ice cream

Tuesday 5 Oct 2021, 16:00 → 18:00 Europe/Zurich

Hannah Bossi (Yale University (US)), Muhammad Ansar Iqbal (University of California Los Angeles (US)), Tara Nanut Petric (CERN), Tomas Herman (Czech Technical University in Prague (CZ))

(No registration needed)

This year we gaze into the exciting world of machine learning and its applications in high energy physics.

After digging into ice cream (unfortunately still only virtually), outstanding speakers will present exciting prospects of machine learning and their application in high energy physics, and reply to the questions of curious young researchers.

The event is organized jointly by the early-career representatives of ALICE, ATLAS, CMS, and LHCb. Among other things, we aim to help junior scientists become aware and involved in topics beyond their current work. This is crucial for the future of our field, because junior scientists make up most of our community.

The event is essentially targeted to a young audience, but everyone is warmly welcome!

So...

Come for (virtual) ice cream, stay for the physics!

 

Zoom: https://cern.zoom.us/j/67794605131?pwd=YTltR1N2RnBjMUhDMGUwSnRPTjRRdz09

Poster designed by Muhammad Ansar Iqbal from CMS.

1 Introduction to machine learning in high energy physics

Speaker: Gregor Kasieczka (Hamburg University (DE))

DeepLearning_IceCream_2021.pdf

2 Graph neural networks

Speaker: Nikita Kazeev (Yandex School of Data Analysis (RU))

GraphNN_CERN_ice_cream.pdf

GraphNN_CERN_ice_cream.pptx

3 Generative Models and Where to Find Them in HEP

Speaker: Michael Aaron Kagan (SLAC National Accelerator Laboratory (US))

Kagan_Oct5_2021.pdf

4 BDT, shallow and deep neural network techniques for analysis and detector reconstruction

Speaker: Gian Michele Innocenti (CERN)

20211005_Innocenti.pdf