Guest Speaker: Daniel Murnane, Postdoctoral Researcher at Berkeley Lab
Hosted By: Savannah Thais, Associate Research Scientist in the Data Science Institute
This will be a HYBRID event. Please indicate on your registration if you will attend virtually or in-person.
In-Person Location: Northwest Corner Building, 14th Floor (DSI Suite) - 550 W 120th St, New York, NY 10027
Virtual: Zoom link to be sent upon registration
Multi-Tasking ML for Point Clouds at the LHC
Abstract: The Large Hadron Collider is one of the world's most data-intensive experiments. Every second, millions of collisions are processed, each one resembling a jigsaw puzzle with thousands of pieces. With the upcoming upgrade to the High Luminosity LHC, this problem will only become more complex. To make sense of this data, deep learning techniques are increasingly being used. For example, graph neural networks & transformers have proven effective at handling point cloud tasks such as track reconstruction & jet tagging. In this talk, I will review the point cloud problems in collider physics & recent deep learning solutions investigated by the Exatrkx project - an initiative to implement innovative algorithms for HEP at exascale. These architectures can accurately perform tracking & tagging with low latency, even in the high luminosity regime. Additionally, I will explore how multi-tasking & multi-modal networks can combine several of these different tasks.