Related papers: Photon Classification with Gradient Boosted Trees …
A first measurement of beam spin asymmetries for $\pi^+\pi^0$ and $\pi^-\pi^0$ pairs in semi-inclusive deep inelastic scattering is reported. The asymmetries in the dihadron angular distributions were measured from the scattering of a 10.6…
Dihadron beam spin asymmetries provide a wide range of insights into nucleon structure and hadronization. Recent measurements at CLAS12 provide the first empirical evidence of nonzero $G_1^\perp$, the parton helicity-dependent dihadron…
In the context of nucleon structure studies, Generalized Parton Distributions (GPDs) are crucial for understanding the correlation between the longitudinal momentum and the transverse position of partons inside the nucleon. A privileged…
The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees from airborne LiDAR data. To enable efficient processing by a deep convolutional neural network (CNN), we…
The CLAS experiment E02-104, part of the EG2 run at Jefferson Lab, was performed to study the hadronization process using semi inclusive deep inelastic scattering off nuclei. Electron beam energy of 5 GeV and the CLAS large acceptance…
Particle identification is one of the core tasks in the data analysis pipeline at the Large Hadron Collider (LHC). Statistically, this entails the identification of rare signal events buried in immense backgrounds that mimic the properties…
We introduce a new experimental effort at Jefferson Lab (JLab) to precisely measure the ratios of charged pion electroproduction in Semi-Inclusive Deep Inelastic Scattering (SIDIS) from $^2$D, $^3$He, and $^3$H targets \cite{c12-21-004}.…
A novel deep neural network classifier, a ``Particle transformer'' (PaRT), is introduced for the identification of highly Lorentz-boosted resonances reconstructed as single, multipronged jets in measurements and searches performed by the…
Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as di-jet resonances, their…
We present an application of a particular machine-learning method (Boosted Decision Trees, BDTs using AdaBoost) to separate stars and galaxies in photometric images using their catalog characteristics. BDTs are a well established machine…
One of the most surprising discoveries made at Jefferson Lab has been the discrepancy in the determinations of the proton's form factor ratio $\mu_p G_E^p/G_M^p$ between unpolarized cross section measurements and the polarization transfer…
The parameterization of the nucleon structure through Generalized Parton Distributions (GPDs) shed a new light on the nucleon internal dynamics. For its direct interpretation, Deeply Virtual Compton Scattering (DVCS) is the golden channel…
An overview is given about the capabilities provided by the JLab 12 GeV Upgrade to measure deeply virtual exclusive processes with high statistics and covering a large kinematics range in the parameters that are needed to allow…
Deep convolutional neural networks accurately classify a diverse range of natural images, but may be easily deceived when designed, imperceptible perturbations are embedded in the images. In this paper, we design a multi-pronged training,…
We demonstrate that the classification of boosted, hadronically-decaying weak gauge bosons can be significantly improved over traditional cut-based and BDT-based methods using deep learning and the jet charge variable. We construct binary…
Reliable large-scale data on the state of forests is crucial for monitoring ecosystem health, carbon stock, and the impact of climate change. Current knowledge of tree species distribution relies heavily on manual data collection in the…
Two popular boosted decsion tree (BDT) methods, Adaptive BDT (AdaBDT) and Gradient BDT (GradBDT) are studied in the classification problem of separating signal from background assuming all trees are weak learners. The following results are…
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on…
Inclusive electron scattering cross sections off a hydrogen target at a beam energy of 10.6 GeV have been measured with data collected from the CLAS12 spectrometer at Jefferson Laboratory. These first absolute cross sections from CLAS12…
High precision measurements of the polarized electron beam-spin asymmetry in semi-inclusive deep inelastic scattering (SIDIS) from the proton have been performed using a 10.6~GeV incident electron beam and the CLAS12 spectrometer at…