Title: Machine learning techniques in searches for$$t\bar{t}$$h in the h → $$b\bar{b}$$ decay channel

Abstract

Study of the production of pairs of top quarks in association with a Higgs boson is one of the primary goals of the Large Hadron Collider over the next decade, as measurements of this process may help us to understand whether the uniquely large mass of the top quark plays a special role in electroweak symmetry breaking. Higgs bosons decay predominantly to b$$\bar{_b}$$, yielding signatures for the signal that are similar to t$$\bar{_t}$$ + jets with heavy flavor. Though particularly challenging to study due to the similar kinematics between signal and background events, such final states (t$$\bar{_t}$$b$$\bar{b}$$) are an important channel for studying the top quark Yukawa coupling. This paper presents a systematic study of machine learning (ML) methods for detecting t$$\bar{_t}$$h in the h → b$$\bar{b}$$ decay channel. Among the seven ML methods tested, we show that neural network models outperform alternative methods. In addition, two neural models used in this paper outperform NeuroBayes, one of the standard algorithms used in current particle physics experiments. We further study the effectiveness of ML algorithms by investigating the impact of feature set and data size, as well as the depth of the networks for neural models. We demonstrate that an extended feature set leads to improvement of performance over basic features. Furthermore, the availability of large samples for training is found to be important for improving the performance of the techniques. For the features and the data set studied here, neural networks of more layers deliver comparable performance to their simpler counterparts.

Authors:

Santos, Robert ^[1]; Nguyen, M. ^[1]; Webster, Jordan ^[2]; Ryu, Soo ^[2]; Adelman, Jahred ^[1]; Chekanov, Sergei ^[2]; Zhou, Jie ^[1]

---

+ Show Author Affiliations

1. Northern Illinois Univ., DeKalb, IL (United States)
2. Argonne National Lab. (ANL), Lemont, IL (United States)

Publication Date:

2017-04-10

Research Org.:

Argonne National Lab. (ANL), Argonne, IL (United States)

Sponsoring Org.:

National Science Foundation (NSF); USDOE Office of Science (SC)

OSTI Identifier:

1373727

Grant/Contract Number:  

AC02-06CH11357

Resource Type:

Accepted Manuscript

Journal Name:

Journal of Instrumentation

Additional Journal Information:

Journal Volume: 12; Journal Issue: 04; Journal ID: ISSN 1748-0221

Publisher:

Institute of Physics (IOP)

Country of Publication:

United States

Language:

English

Subject:

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; Analysis and statistical methods; Data processing methods