scholarly journals Machine Learning Using Rapidity-Mass Matrices for Event Classification Problems in HEP

Universe ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 19
Author(s):  
Sergei V. Chekanov
Keyword(s):  
Machine Learning ◽  
Standard Model ◽  
Mass Matrix ◽  
Hadron Collider ◽  
Feature Space ◽  
New Physics ◽  
Machine Learning Techniques ◽  
Monte Carlo Event ◽  
Classification Problems ◽  
Event Classification

In this work, supervised artificial neural networks (ANN) with rapidity–mass matrix (RMM) inputs are studied using several Monte Carlo event samples for various pp collision processes. The study shows the usability of this approach for general event classification problems. The proposed standardization of the ANN feature space can simplify searches for signatures of new physics at the Large Hadron Collider (LHC) when using machine learning techniques. In particular, we illustrate how to improve signal-over-background ratios in the search for new physics, how to filter out Standard Model events for model-agnostic searches, and how to separate gluon and quark jets for Standard Model measurements.

scholarly journals Exploring End-to-end Deep Learning Applications for Event Classification at CMS

2019 ◽  
Vol 214 ◽  
pp. 06031 ◽  
Author(s):  
Michael Andrews ◽  
Manfred Paulini ◽  
Sergei Gleyzer ◽  
Barnabas Poczos
Keyword(s):  
Deep Learning ◽  
Hadron Collider ◽  
Learning Algorithms ◽  
Open Data ◽  
New Physics ◽  
Machine Learning Techniques ◽  
Detector Response ◽  
Event Classification ◽  
End To End ◽  
High Level

An essential part of new physics searches at the Large Hadron Collider (LHC) at CERN involves event classification, or distinguishing potential signal events from those coming from background processes. Current machine learning techniques accomplish this using traditional hand-engineered features like particle 4-momenta, motivated by our understanding of particle decay phenomenology. While such techniques have proven useful for simple decays, they are highly dependent on our ability to model all aspects of the phenomenology and detector response. Meanwhile, powerful deep learning algorithms are capable of not only training on high-level features, but of performing feature extraction. In computer vision, convolutional neural networks have become the state-of-the-art for many applications. Motivated by their success, we apply deep learning algorithms to low-level detector data from the 2012 CMS Simulated Open Data to directly learn useful features, in what we call, end-to-end event classification. We demonstrate the power of this approach in the context of a physics search and offer solutions to some of the inherent challenges, such as image construction, image sparsity, combining multiple sub-detectors, and de-correlating the classifier from the search observable, among others.

scholarly journals Using Machine Learning for Precision Measurements

2019 ◽  
Vol 214 ◽  
pp. 06022
Author(s):  
Dimitri Bourilkov
Keyword(s):  
Machine Learning ◽  
Signal To Noise Ratio ◽  
Hadron Collider ◽  
New Physics ◽  
Precise Determination ◽  
Machine Learning Techniques ◽  
Test Case ◽  
Mixing Angle ◽  
Learning Techniques ◽  
Electroweak Mixing Angle

The use of machine learning techniques for classification is well established. They are applied widely to improve the signal-to-noise ratio and the sensitivity of searches for new physics at colliders. In this study I explore the use of machine learning for optimizing the output of high precision experiments by selecting the most sensitive variables to the quantity being measured. The precise determination of the electroweak mixing angle at the Large Hadron Collider using linear or deep neural network regressors is developed as a test case.

scholarly journals Machine learning techniques for detecting topological avatars of new physics

2019 ◽  
Vol 377 (2161) ◽  
pp. 20190392 ◽  
Author(s):  
A. J. Bevan
Keyword(s):  
Machine Learning ◽  
Particle Physics ◽  
Data Science ◽  
Hadron Collider ◽  
Nuclear Research ◽  
New Physics ◽  
Machine Learning Techniques ◽  
Beyond The Standard Model ◽  
Learning Techniques ◽  
The Standard Model

The search for highly ionizing particles in nuclear track detectors (NTDs) traditionally requires experts to manually search through samples in order to identify regions of interest that could be a hint of physics beyond the standard model of particle physics. The advent of automated image acquisition and modern data science, including machine learning-based processing of data presents an opportunity to accelerate the process of searching for anomalies in NTDs that could be a hint of a new physics avatar. The potential for modern data science applied to this topic in the context of the MoEDAL experiment at the large Hadron collider at the European Centre for Nuclear Research, CERN, is discussed. This article is part of a discussion meeting issue ‘Topological avatars of new physics’.

scholarly journals A Machine Learning approach to the EFT re-interpretation of the WZjj fully leptonic electroweak production

2021 ◽  
Vol 2105 (1) ◽  
pp. 012011
Author(s):  
Konstantinos Bachas ◽  
Ioannis Karkanias ◽  
Eirini Kasimi ◽  
Christos Leonidis ◽  
Chara Petridou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Standard Model ◽  
Vector Boson ◽  
New Physics ◽  
Effective Field ◽  
Machine Learning Techniques ◽  
Atlas Collaboration ◽  
The Standard Model ◽  
Two Jets ◽  
Integrated Luminosity

Abstract In this paper we study the use of Machine Learning techniques to set constraints on indirect signatures of physics beyond the Standard Model in Vector Boson Scattering (VBS), in the electroweak (EWK) production of self-interacting W ± Z bosons in association with two jets. The WZ fully leptonic channel has been extensively studied by the ATLAS Collaboration at the LHC and we are about to provide results using the full Run 2 data corresponding to an integrated luminosity of 139fb −1. The EWK production of the WZ in association with two jets has been already observed at 36fb −1 with an observed significance of 5.3 standard deviations. A factor of four increase in the integrated luminosity provides an opportunity to check for deviations from the Standard Model (SM) predictions, in particular for model independent, indirect searches for New Physics. Such searches can be realized in the context of an extension of the SM in terms of an Effective Field Theory (EFT) formalism, providing a way to quantify possible deviations from the Standard Model. The EFT Lagrangian besides the Standard Model terms comprises contributions from higher dimension operators, their effect being determined by the strength of their corresponding parameters (Wilson coefficients scaled to the appropriate power of Λ, indicating the scale of the appearance of New Physics). In this paper an attempt is made to search for New Physics effects in the WZjj production, using state-of-the-art machine learning models where diverse network architectures are effectively combined into ensembles trained on the outcomes of base learners maximizing performance. The base learners are trained to identify pure WZjj signal events originating from the effect of EFT operators, from WZjj background events originating from strong (QCD) or EWK WZjj processes. We investigate the utilization of the ensemble model response in estimating the sensitivity of WZjj events in some of the dimension-8 EFT operators and compare the results to sensitive kinematic variables traditionally used to constrain the EFT operator effects.

A Comparative Study of Different Machine Learning Algorithms for Disease Prediction

2017 ◽  
Vol 7 (7) ◽  
pp. 172
Author(s):  
Anantvir Singh Romana
Keyword(s):  
Machine Learning ◽  
Subsequent Treatment ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Disease Prediction ◽  
Classification Problems ◽  
Learning Techniques ◽  
Neural Network Classifiers ◽  
Diagnostic Detection

Accurate diagnostic detection of the disease in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Naïve bayes, J48 Decision Tree and neural network classifiers breast cancer and diabetes datsets.

scholarly journals B PHYSICS AT LHCb

2008 ◽  
Vol 23 (32) ◽  
pp. 5117-5136 ◽  
Author(s):  
MONICA PEPE ALTARELLI ◽  
FREDERIC TEUBERT
Keyword(s):  
Large Hadron Collider ◽  
Standard Model ◽  
B Physics ◽  
Hadron Collider ◽  
New Physics ◽  
Concise Review ◽  
The Standard Model ◽  
And Performance ◽  
Detector Design

LHCb is a dedicated detector for b physics at the LHC (Large Hadron Collider). In this paper we present a concise review of the detector design and performance together with the main physics goals and their relevance for a precise test of the Standard Model and search of New Physics beyond it.

scholarly journals Exploiting node metadata to predict interactions in large networks using graph embedding and neural networks

2021 ◽  
Author(s):  
Rogini Runghen ◽  
Daniel B Stouffer ◽  
Giulio Valentino Dalla Riva
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Link Prediction ◽  
Graph Embedding ◽  
Feature Space ◽  
Machine Learning Techniques ◽  
Large Networks ◽  
Data Set ◽  
Learning Techniques ◽  
Low Dimensional

Collecting network interaction data is difficult. Non-exhaustive sampling and complex hidden processes often result in an incomplete data set. Thus, identifying potentially present but unobserved interactions is crucial both in understanding the structure of large scale data, and in predicting how previously unseen elements will interact. Recent studies in network analysis have shown that accounting for metadata (such as node attributes) can improve both our understanding of how nodes interact with one another, and the accuracy of link prediction. However, the dimension of the object we need to learn to predict interactions in a network grows quickly with the number of nodes. Therefore, it becomes computationally and conceptually challenging for large networks. Here, we present a new predictive procedure combining a graph embedding method with machine learning techniques to predict interactions on the base of nodes' metadata. Graph embedding methods project the nodes of a network onto a---low dimensional---latent feature space. The position of the nodes in the latent feature space can then be used to predict interactions between nodes. Learning a mapping of the nodes' metadata to their position in a latent feature space corresponds to a classic---and low dimensional---machine learning problem. In our current study we used the Random Dot Product Graph model to estimate the embedding of an observed network, and we tested different neural networks architectures to predict the position of nodes in the latent feature space. Flexible machine learning techniques to map the nodes onto their latent positions allow to account for multivariate and possibly complex nodes' metadata. To illustrate the utility of the proposed procedure, we apply it to a large dataset of tourist visits to destinations across New Zealand. We found that our procedure accurately predicts interactions for both existing nodes and nodes newly added to the network, while being computationally feasible even for very large networks. Overall, our study highlights that by exploiting the properties of a well understood statistical model for complex networks and combining it with standard machine learning techniques, we can simplify the link prediction problem when incorporating multivariate node metadata. Our procedure can be immediately applied to different types of networks, and to a wide variety of data from different systems. As such, both from a network science and data science perspective, our work offers a flexible and generalisable procedure for link prediction.

scholarly journals Utilizing Unsupervised Machine Learning in BSM Physics Searches At The LHC

2020 ◽  
Vol 245 ◽  
pp. 06021
Author(s):  
Adam Leinweber ◽  
Martin White
Keyword(s):  
Machine Learning ◽  
Large Hadron Collider ◽  
Hadron Collider ◽  
New Physics ◽  
Machine Learning Technique ◽  
Unsupervised Machine Learning ◽  
Learning Technique ◽  
Bsm Physics ◽  
Supersymmetric Particles ◽  
One Machine

Recent searches for supersymmetric particles at the Large Hadron Collider have been unsuccessful in detecting any BSM physics. This is partially because the exact masses of supersymmetric particles are not known, and as such, searching for them is very difficult. The method broadly used in searching for new physics requires one to optimise on the signal being searched for, potentially suppressing sensitivity to new physics which may actually be present that does not resemble the chosen signal. The problem with this approach is that, in order to detect something with this method, one must already know what to look for. I will showcase one machine-learning technique that can be used to define a “signal-agnostic” search. This is a search that does not make any assumptions about the signal being searched for, allowing it to detect a signal in a more general way. This method is applied to simulated BSM physics data and the results are explored.

Machine Learning Applications in Mega-Text Processing

2010 ◽  
pp. 325-347 ◽  
Author(s):  
Marina Sokolova ◽  
Stan Szpakowicz
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Opinion Mining ◽  
Personal Information ◽  
Text Processing ◽  
Machine Learning Techniques ◽  
Classification Problems ◽  
The Status ◽  
Machine Learning Applications ◽  
Applications Of Machine Learning

This chapter presents applications of machine learning techniques to problems in natural language processing that require work with very large amounts of text. Such problems came into focus after the Internet and other computer-based environments acquired the status of the prime medium for text delivery and exchange. In all cases which the authors discuss, an algorithm has ensured a meaningful result, be it the knowledge of consumer opinions, the protection of personal information or the selection of news reports. The chapter covers elements of opinion mining, news monitoring and privacy protection, and, in parallel, discusses text representation, feature selection, and word category and text classification problems. The applications presented here combine scientific interest and significant economic potential.

Sign in / Sign up

Export Citation Format

Share Document