Machine learning, which builds on ideas in computer science, statistics, and optimization, focuses on developing algorithms to identify patterns and regularities in data, and using these learned patterns to make predictions on new observations. Boosted by its industrial and commercial applications, the field of machine learning is quickly evolving and expanding. Recent advances have seen great success in the realms of computer vision, natural language processing, and broadly in data science. Many of these techniques have already been applied in particle physics, for instance for particle identification, detector monitoring, and the optimization of computer resources. Modern machine learning approaches, such as deep learning, are only just beginning to be applied to the analysis of High Energy Physics data to approach more and more complex problems. This lectures will review the framework behind machine learning and discuss some recent developments in the field.
Michael Kagan received his Ph.D. in Experimental High Energy Physics from Harvard in 2012 and was a postdoctoral research associate at SLAC from 2012-2016, both while performing research as a member of the ATLAS experiment. Since 2016, Michael has been a Panofsky fellow at SLAC continuing to work on the ATLAS experiment. A major theme in his research has been building connections between High Energy Physics and Machine Learning in order to develop new and powerful tools to apply to the analysis of high energy collider data.