Abstract
Machine learning is an important applied research area in particle physics, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas in machine learning in particle physics with a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.
Highlights
The main objectives of particle physics in the post-Higgs boson discovery era is to exploit the full physics potential of both the Large Hadron Collider (LHC) and its upgrade, the high luminosity LHC (HL-LHC), in addition to present and future neutrino experiments
Disadvantages of using external tools are that there are too many choices, they are not guaranteed to be supported over the lifetime of particle physics experiments, and it can be difficult to adapt them to high-energy physics (HEP) specific requirements which may not be among the priorities of the Machine learning (ML) community
As particle physics moves into the post-Higgs boson discovery era, the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments will require increasingly more powerful identification and reconstruction algorithms to extract rare signals from copious and challenging backgrounds
Summary
Discovery science provides a challenge that attracts brilliant minds eager to push the boundaries of scientific understanding of nature. The goal is to achieve a vibrant collaboration between the data science and high-energy physics communities by finding a common language and working together to further science. Both communities can benefit from such collaboration. The HEP community needs to define its challenges in a language that the ML community can understand. This may involve stripping the domain knowledge entirely, or retaining necessary information with clear and concise explanations as to its relevance. Ideas and solutions provided by both communities should be presented in an understandable way for scientists without in-depth knowledge
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
