Abstract
Machine Learning (ML) techniques are rapidly finding a place among the methods of High Energy Physics data analysis. Different approaches are explored concerning how much effort should be put into building high-level variables based on physics insight into the problem, and when it is enough to rely on low-level ones, allowing ML methods to find patterns without explicit physics model. In this paper we continue the discussion of previous publications on the CP state of the Higgs boson measurement of the H to tau tau decay channel with the consecutive tau^pm to rho^pm nu; rho^pm to pi^pm pi^0 and tau^pm to a_1^pm nu; a_1^pm to rho^0 pi^pm to 3 pi^pm cascade decays. The discrimination of the Higgs boson CP state is studied as a binary classification problem between CP-even (scalar) and CP-odd (pseudoscalar), using Deep Neural Network (DNN). Improvements on the classification from the constraints on directly non-measurable outgoing neutrinos are discussed. We find, that once added, they enhance the sensitivity sizably, even if only imperfect information is provided. In addition to DNN we also evaluate and compare other ML methods: Boosted Trees (BT), Random Forest (RF) and Support Vector Machine (SVN).
Highlights
Machine learning (ML) techniques are finding an increasing number of applications in high-energy physics phenomenology
Different approaches are explored concerning how much effort should be put into building high-level variables based on physics insight into the problem, and when it is enough to rely on low-level ones, allowing ML methods to find patterns without an explicit physics model
In previous papers [20,21] we have demonstrated that ML methods, like deep neural networks (DNNs) [22], can serve as a promising analysis method to constrain the Higgs boson CP state in the decay channel H → ττ
Summary
Machine learning (ML) techniques are finding an increasing number of applications in high-energy physics phenomenology. With the Tevatron and the LHC experiments it has became a standard analysis tool. ML techniques are used for event selection, event classification, background suppression for the signal events of the interest, etc. For a recent comprehensive review, see Refs. Over the last years the most significant progress in phenomenology due to ML techniques (in particular the recent developments in neural network methods) has been in hadronic jet reconstruction and classification: jet substructure, flavor, charge, and mass. Some long-standing challenges of more classical algorithms have been addressed; see, e.g., Refs. Some long-standing challenges of more classical algorithms have been addressed; see, e.g., Refs. [4,5,6,7,8,9,10]
Sign-in/Register to view highlights & summary 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.
