Conveners
Session IV: Session IV
- Xifeng Ruan (University of the Witwatersrand (ZA))
As no definite signs of new physics has been observed at the LHC data yet, alternate approaches have been proposed. These include looking at unusual topologies, and using existing measurements to constrain models (CONTUR). In tis overview, I will discuss some of the recent developments along these directions, covering jet substructure methods to identify semivisible jets, a realistic detector...
This project studies a robust anti-QCD tagger with mass de-correlating jet image data produced using the pre-processing method introduced in arXiv: 1903.02032. A semi-supervised (where data is only trained on background) learning anomaly detection approach using convolutional autoencoder neural networks is explored as an anti-QCD tagger in this study. Jet image data is used to train the...
We propose a new approach to search for new resonances beyond the Standard Model (SM) of particle physics in topological configurations using Machine Learning techniques. This involves a novel classification procedure based on a combination of weak-supervision and full-supervision in conjunction with Deep Neural Network algorithms. The performance of this strategy is evaluated on the...
Unlike supervised learning which is known to assume a full knowledge of the underlying model, weak supervision allows with partial knowledge to extract new information from the data.
The objective of this study is to set up the search for heavy resonances at the electroweak scale with topological requirements. These resonances are expected to be produced with different production mechanisms....
What is typically referred to as the inverse problem in High Energy Physics (HEP) can be described as the use of data to extract key information to build new a theory. The search of new resonances beyond the Standard Model (SM) involves the use of different Machine Learning techniques. For this purpose, based on the recent and major successes in the field of deep learning, particularly Deep...
In the search for new physics Beyond the Standard Model, MVA techniques are used to extract specific signal from Standard Model background processes. In this study weakly-supervised machine learning techniques are developed and evaluated using the ATLAS experiment, di-lepton (e±μ∓) final state data, in the H → Sh search. These weakly-supervised techniques use labelled background data to...
Motivated by the statistically significant excesses in the multi-lepton final states compatible with physics at the electroweak scale, here we attempt a direct search for a heavy scalar resonance in the Z and photon system in the LHC Run 2 dataset. The study aims to extract the signal process using a machine learning algorithm.
Satellite data enables the efficient mapping and monitoring of the earth’s resources, ecosystems, and events. Machine Learning can be applied to this data to predict weather conditions. Machine Learning techniques can be used to model and extract useful information out of a data stream. This helps governments and industries to share information, to make informed decisions, to act on time and...
In this article we search for a heavy resonance decaying into two photons in association with $b$ jets. The search uses $139~\mbox{fb\(^{-1}\)}$ proton--proton collision data taken from the ATLAS detector at the centre-of mass energy of 13TeV during 2015 to 2018. Three models are tested in this final state. A Higgs boson like heavy scalar $X$ produced with top quarks, $b$ quarks or $Z$ boson...
The 4-lepton final state is a clean and important signal that is being studied at the ATLAS detector. In this study, we focus on four leptons originated from the $R\rightarrow SH\rightarrow 4\ell+E^{miss}_{T}$ signal. $R$ is a scalar boson produced via gluon--gluon fusion and decays to two lighter scalar bosons, $S$ and $H$. The $S$ decays to a pair of Standard Model of particle physics...