scholarly journals Quasi anomalous knowledge: searching for new physics with embedded knowledge

2021 ◽  
Vol 2021 (6) ◽  
Author(s):  
Sang Eon Park ◽  
Dylan Rankin ◽  
Silviu-Marian Udrescu ◽  
Mikaeel Yunus ◽  
Philip Harris
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Hadron Collider ◽  
New Physics ◽  
Network Architectures ◽  
Cern Large Hadron Collider ◽  
Learning Techniques ◽  
Embedded Knowledge ◽  
New Strategy ◽  
New Phenomena

Abstract Discoveries of new phenomena often involve a dedicated search for a hypothetical physics signature. Recently, novel deep learning techniques have emerged for anomaly detection in the absence of a signal prior. However, by ignoring signal priors, the sensitivity of these approaches is significantly reduced. We present a new strategy dubbed Quasi Anomalous Knowledge (QUAK), whereby we introduce alternative signal priors that capture some of the salient features of new physics signatures, allowing for the recovery of sensitivity even when the alternative signal is incorrect. This approach can be applied to a broad range of physics models and neural network architectures. In this paper, we apply QUAK to anomaly detection of new physics events at the CERN Large Hadron Collider utilizing variational autoencoders with normalizing flow.

scholarly journals Finding new physics without learning about it: anomaly detection as a tool for searches at colliders

2021 ◽  
Vol 81 (1) ◽  
Author(s):  
M. Crispim Romão ◽  
N. F. Castro ◽  
R. Pedro
Keyword(s):  
Anomaly Detection ◽  
New Physics ◽  
Machine Learning Techniques ◽  
Detection Methods ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Detection Techniques ◽  
Learning Techniques ◽  
New Strategy

AbstractIn this paper we propose a new strategy, based on anomaly detection methods, to search for new physics phenomena at colliders independently of the details of such new events. For this purpose, machine learning techniques are trained using Standard Model events, with the corresponding outputs being sensitive to physics beyond it. We explore three novel AD methods in HEP: Isolation Forest, Histogram-Based Outlier Detection, and Deep Support Vector Data Description; alongside the most customary Autoencoder. In order to evaluate the sensitivity of the proposed approach, predictions from specific new physics models are considered and compared to those achieved when using fully supervised deep neural networks. A comparison between shallow and deep anomaly detection techniques is also presented. Our results demonstrate the potential of semi-supervised anomaly detection techniques to extensively explore the present and future hadron colliders’ data.

scholarly journals Searches for extra spatial dimensions with the CMS detector at the LHC

2015 ◽  
Vol 30 (15) ◽  
pp. 1540017 ◽  
Author(s):  
Greg Landsberg
Keyword(s):  
Hadron Collider ◽  
Center Of Mass ◽  
New Physics ◽  
Current Status ◽  
Beyond The Standard Model ◽  
Cern Large Hadron Collider ◽  
The Standard Model ◽  
Cms Detector ◽  
Spatial Dimensions ◽  
8 Tev

The success of the first three years of operations of the CERN Large Hadron Collider (LHC) at center-of-mass energies of 7 TeV and 8 TeV radically changed the landscape of searches for new physics beyond the Standard Model (BSM) and our very way of thinking about its possible origin and its hiding place. Among the paradigms of new physics that have been probed quite extensively at the LHC, are various models that predict the existence of extra spatial dimensions. In this review, the current status of searches for extra dimensions with the Compact Muon Solenoid (CMS) detector is presented, along with prospects for future searches at the full energy of the LHC, expected to be reached in the next few years.

scholarly journals Detecting an axion-like particle with machine learning at the LHC

2021 ◽  
Vol 2021 (11) ◽  
Author(s):  
Jie Ren ◽  
Daohan Wang ◽  
Lei Wu ◽  
Jin Min Yang ◽  
Mengchao Zhang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Mass Range ◽  
New Physics ◽  
Machine Learning Techniques ◽  
Global Symmetry ◽  
Sequential Decay ◽  
Production Processes ◽  
Learning Techniques ◽  
Photon Coupling

Abstract Axion-like particles (ALPs) appear in various new physics models with spon- taneous global symmetry breaking. When the ALP mass is in the range of MeV to GeV, the cosmology and astrophysics bounds are so far quite weak. In this work, we investi- gate such light ALPs through the ALP-strahlung production processes pp → W±a, Za with the sequential decay a → γγ at the 14 TeV LHC with an integrated luminosity of 3000 fb−1 (HL-LHC). Building on the concept of jet image which uses calorimeter towers as the pixels of the image and measures a jet as an image, we investigate the potential of machine learning techniques based on convolutional neural network (CNN) to identify the highly boosted ALPs which decay to a pair of highly collimated photons. With the CNN tagging algorithm, we demonstrate that our approach can extend current LHC sensitivity and probe the ALP mass range from 0.3 GeV to 5 GeV. The obtained bounds are stronger than the existing limits on the ALP-photon coupling.

Benchmarking Deep Neural Network Architectures for Machining Tool Anomaly Detection

2020 ◽  
Vol 4 (2) ◽  
pp. 20190039
Author(s):  
Tejas Puranik ◽  
Aroua Gharbi ◽  
Burak Bagdatli ◽  
Olivia Pinon Fischer ◽  
Dimitri N. Mavris
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Deep Neural Network ◽  
Network Architectures ◽  
Neural Network Architectures

scholarly journals Electroweak gauge-boson production in association with b jets at Hadron Colliders

2015 ◽  
Vol 30 (16) ◽  
pp. 1530042 ◽  
Author(s):  
F. Febres Cordero ◽  
L. Reina
Keyword(s):  
Large Hadron Collider ◽  
Gauge Boson ◽  
Hadron Collider ◽  
New Physics ◽  
Distribution Functions ◽  
Experimental Measurements ◽  
Cern Large Hadron Collider ◽  
Electroweak Gauge Boson ◽  
Theoretical Predictions ◽  
B Quark

The production of both charged and neutral electroweak gauge bosons in association with b jets has attracted a lot of experimental and theoretical attention in recent years because of its central role in the physics programs of both the Fermilab Tevatron and the CERN Large Hadron Collider. The improved level of accuracy achieved both in the theoretical predictions and experimental measurements of these processes can promote crucial developments in modeling b-quark jets and b-quark parton distribution functions, and can provide a more accurate description of some of the most important backgrounds to the measurement of Higgs-boson couplings and several new physics searches. In this paper, we review the status of theoretical predictions for cross sections and kinematic distributions of processes in which an electroweak gauge boson is produced in association with up to two b jets in hadronic collisions, namely [Formula: see text], pp → V + 1b jet and [Formula: see text], pp → V + 2b jets with V = W±, Z/γ*, γ. Available experimental measurements at both the Fermilab Tevatron and the CERN Large Hadron Collider are also reviewed and their comparison with theoretical predictions is discussed.

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 SEARCH AND IDENTIFICATION OF EXTRA SPATIAL DIMENSIONS AT LHC

2005 ◽  
Vol 20 (11) ◽  
pp. 2232-2236 ◽  
Author(s):  
ERIK W. DVERGSNES ◽  
PER OSLAND ◽  
ALEXANDER A. PANKOV ◽  
NELLO PAVER
Keyword(s):  
Large Hadron Collider ◽  
Pair Production ◽  
Extra Dimensions ◽  
Hadron Collider ◽  
New Physics ◽  
Lepton Pair ◽  
Cern Large Hadron Collider ◽  
Lepton Pair Production ◽  
Center Edge ◽  
Spatial Dimensions

We present an analysis, based on the center–edge asymmetry, to distinguish effects of extra dimensions within the Arkani-Hamed–Dimopoulos–Dvali (ADD) and Randall–Sundrum (RS) scenarios from other new physics effects in lepton-pair production at the CERN Large Hadron Collider LHC. Spin-2 and spin-1 exchange can be distinguished up to an ADD cutoff scale, MH, of about 5 TeV, at the 95% CL. In the RS scenario, spin-2 resonances can be identified in most of the favored parameter space.

scholarly journals Anomaly Detection Using XGBoost Ensemble of Deep Neural Network Models

2021 ◽  
Vol 21 (3) ◽  
pp. 175-188
Author(s):  
Sumaiya Thaseen Ikram ◽  
Aswani Kumar Cherukuri ◽  
Babu Poorva ◽  
Pamidi Sai Ushasree ◽  
Yishuo Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Network Models ◽  
Neural Network Models ◽  
Detection Model ◽  
Detection Systems ◽  
Learning Techniques

Abstract Intrusion Detection Systems (IDSs) utilise deep learning techniques to identify intrusions with maximum accuracy and reduce false alarm rates. The feature extraction is also automated in these techniques. In this paper, an ensemble of different Deep Neural Network (DNN) models like MultiLayer Perceptron (MLP), BackPropagation Network (BPN) and Long Short Term Memory (LSTM) are stacked to build a robust anomaly detection model. The performance of the ensemble model is analysed on different datasets, namely UNSW-NB15 and a campus generated dataset named VIT_SPARC20. Other types of traffic, namely unencrypted normal traffic, normal encrypted traffic, encrypted and unencrypted malicious traffic, are captured in the VIT_SPARC20 dataset. Encrypted normal and malicious traffic of VIT_SPARC20 is categorised by the deep learning models without decrypting its contents, thus preserving the confidentiality and integrity of the data transmitted. XGBoost integrates the results of each deep learning model to achieve higher accuracy. From experimental analysis, it is inferred that UNSW_ NB results in a maximal accuracy of 99.5%. The performance of VIT_SPARC20 in terms of accuracy, precision and recall are 99.4%. 98% and 97%, respectively.

scholarly journals Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes

2020 ◽  
Vol 34 (04) ◽  
pp. 4477-4484
Author(s):  
Ranganath Krishnan ◽  
Mahesh Subedar ◽  
Omesh Tickoo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Empirical Bayes ◽  
Hierarchical Modeling ◽  
Variational Inference ◽  
Maximum Likelihood Estimates ◽  
Network Architectures ◽  
Posterior Distributions ◽  
Stochastic Variational Inference ◽  
Learning Techniques

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying priors and approximate posterior distributions over neural network weights. Specifying meaningful weight priors is a challenging problem, particularly for scaling variational inference to deeper architectures involving high dimensional weight space. We propose MOdel Priors with Empirical Bayes using DNN (MOPED) method to choose informed weight priors in Bayesian neural networks. We formulate a two-stage hierarchical modeling, first find the maximum likelihood estimates of weights with DNN, and then set the weight priors using empirical Bayes approach to infer the posterior with variational inference. We empirically evaluate the proposed approach on real-world tasks including image classification, video activity recognition and audio classification with varying complex neural network architectures. We also evaluate our proposed approach on diabetic retinopathy diagnosis task and benchmark with the state-of-the-art Bayesian deep learning techniques. We demonstrate MOPED method enables scalable variational inference and provides reliable uncertainty quantification.

Sign in / Sign up

Export Citation Format

Share Document