Speaker
Description
As datasets in particle physics get progressively larger, algorithms to swiftly and accurately process this data have become increasingly complex. Machine Learning (ML) has emerged as a solution to tackle several of the challenges experiments face: to efficiently select and reconstruct interesting observational data, to enhance sensitivity to increasingly rare processes and to efficiently generate accurate simulations of complex physical systems.
In this talk, I will give an overview of how ML is becoming an integral part of how we do particle physics research; from contributing to the discovery of the Higgs boson in 2012, to helping experiments at the future High Luminosity LHC process an amount of data comparable to 5% of the total internet traffic. We will especially focus on the role of Deep Learning in tackling future computational challenges in high energy physics.