Related papers: Re-optimization of a deep neural network model for…
Most techniques for explainable machine learning focus on feature attribution, i.e., values are assigned to the features such that their sum equals the prediction. Example attribution is another form of explanation that assigns weights to…
Previously published data on inclusive neutral and charged current e+p and e-p deep inelastic scattering from HERA have been combined. The new, model-independent method of combining the measured cross sections takes full account of…
Charged current inclusive neutrino-nucleus cross sections are evaluated using the superscaling model for quasielastic scattering and its extension to the pion production region. The contribution of two-particle-two-hole vector…
To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy.…
The planned in-ice radio array of IceCube-Gen2 at the South Pole will provide unprecedented sensitivity to ultra-high-energy (UHE) neutrinos in the EeV range. The ability of the detector to measure the neutrino's energy and direction is of…
Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…
Event-by-event QCD kinetic theory simulations are hindered by the large numerical cost of evaluating the high-dimensional collision integral in the Boltzmann equation. In this work, we show that a neural network can be used to obtain an…
The impact of nonlinear effects in the diffractive observables that will be measured in future electron-ion collisions is investigated. We present, for the first time, the predictions for the diffractive structure function and reduced cross…
The accurate and efficient prediction of crack propagation in dielectric materials is a critical challenge in structural health monitoring and the design of smart systems. This work presents a hybrid modeling framework that combines an…
Accurate approximation of the sampling distribution of nonparametric kernel density estimators is crucial for many statistical inference problems. Since these estimators have complex asymptotic distributions, bootstrap methods are often…
The influence of dispersion on the differential scattering cross section in the vicinity of the first diffraction minimum is revisited for collision energies between 200 and 450 MeV. Transient nuclear excitations in the giant resonance…
We present results using a new scaling variable, xi_w in modeling electron- and neutrino-nucleon scattering cross sections with effective leading order PDFs.Our model uses all inelastic charged lepton F_2 data (SLAC/BCDMS/NMC/HERA), and…
Neural networks have been demonstrated to be able to accelerate the modeling and inverse design of optical and electromagnetic devices by serving as fast surrogates for electromagnetic solvers. Nevertheless, such neural networks can be…
We present a hybrid approach combining isogeometric analysis with deep operator networks to solve electromagnetic scattering problems. The neural network takes a computer-aided design representation as input and predicts the electromagnetic…
We introduce general scattering transforms as mathematical models of deep neural networks with l2 pooling. Scattering networks iteratively apply complex valued unitary operators, and the pooling is performed by a complex modulus. An…
A fully connected neural network was trained to model the K-shell ionization cross sections based on two input features: the atomic number and the incoming electron overvoltage. The training utilized a recent, updated compilation of…
The coplete analysis of the model-independent leading radiative corrections to cross-section and polarization observables in semi-inclusive deep-inelastic electron-nucleus scattering with detection of a proton and scattered electron in…
A deep neural network (DNN) model consisting of two hidden layers was proposed for predicting the immediate environments of specific atoms based on X-ray absorption near-edge spectra (XANES). The output layer of the DNN can be adjusted to…
We perform a combined analysis of inclusive electron scattering data from $A=3$ nuclei in the deep-inelastic and quasielastic scattering regions, using Monte Carlo analysis methods and the nuclear weak binding approximation to establish the…
We calculate the energy dependence of inclusive and diffractive neutrino-nucleus deep-inelastic scattering cross sections within the dipole picture, focusing on the ultra-high-energy regime. We predict an up to $\sim 10\%$ nuclear…