Nature Reviews Physics: Machine learning in theoretical and experimental high energy physics

Photo by Michael Dziedzic on Unsplash

Learn more Watch now Add to Calendar 10/12/2022 04:00 PM 10/12/2022 05:10 PM Europe/London Nature Reviews Physics: Machine learning in theoretical and experimental high energy physics Photo by Michael Dziedzic on Unsplash Location of the event
Wednesday 12 Oct 2022
Time: 16:00 - 17:10

Event type

Virtual seminar

Audience type



Machine learning is no longer restricted to data analysis. It is currently used in theory, experiment and simulation. This is a sign that AI is becoming pervasive in all traditional aspects of research. However, are theorists, experimentalists and computational scientists aware of each other’s problems and the solutions developed to tackle them? Are researchers working in different areas of physics aware of developments in other areas? Machine learning has been used in experimental high energy physics since the 1990s, later enabling the data analysis that made possible the discovery of the Higgs boson. Today machine learning is not only an integral part of the data acquisition and analysis workflows in high energy physics experiments, but it also provides new tools for theorists. Therefore, machine learning is expected to make a large contribution to the ongoing search for new physics.

Watch now 

Chair - Professor Adrian Bevan

About the event

In this event, we will hear from Associate Professor James Halverson and Dr Jennifer Ngadiuba.

Associate Professor James Halverson - Machine Learning for Theoretical Physics

Machine learning has now also been applied to theoretical high energy physics, for instance in the construction of particle physics theories or in string theory. Unexpected deep connections between neural network theory and quantum field theory and the framework underlying particle physics, have all been uncovered and are currently being explored.

Dr Jennifer Ngadiuba - Machine Learning for High Energy Physics

Particle physics experiments are constantly increasing in both sophistication of detector technology and intensity of particle beams. The resulting big-data challenge faced by next generation of HEP experimental setups will require

machine learning to be deployed at every stage of the data processing up to the real-time subsytems characterized by stringent system constraints in terms of computational speed, resource usage, and energy consumption. Modern ML algorithms provide promising solutions thanks to their capacity of extracting the most useful physics information from highly complex data in a scalable way when full parallelisation is exploited on suitable hardware. This talk will cover a few examples of applications of ML at the Large Hadron Collider and at neutrino experiments.



Professor Ben MacArthur

Director of AI for Science and Government, Deputy Programme Director for Health and Medical Sciences, and Turing Fellow

Professor Jonathan Rowe

AI for Science and Government Programme Chair, Programme Director for Data Science for Science, and Turing Fellow