Related papers: Deeply Learning Deep Inelastic Scattering Kinemati…

We investigate hadron production in deep inelastic lepton-nucleus scattering in the kinematic regime of the HERMES experiment. Our calculations are carried out in the framework of a BUU transport model which contains the Lund event…

Aims: The aim of this work is to study the application of the artificial neural networks guided by the autoencoder architecture as a method for precise reconstruction of the neutron star equation of state, using their observable parameters:…

An introduction and summary is given of the main results achieved by working group 1: Structure Functions in Deep Inelastic Scattering at HERA. The prospects were discussed of future measurements of the structure functions $F_{2}, F_{L},…

We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4x4 Ising model. Using its success at this task, we motivate the study of the larger 8x8 Ising model, showing that the…

Accurate interpolation of seismic data is crucial for improving the quality of imaging and interpretation. In recent years, deep learning models such as U-Net and generative adversarial networks have been widely applied to seismic data…

We introduce a deep learning (DL) framework for inverse problems in imaging, and demonstrate the advantages and applicability of this approach in passive synthetic aperture radar (SAR) image reconstruction. We interpret image recon-…

Nonlinear electromagnetic (EM) inverse scattering is a quantitative and super-resolution imaging technique, in which more realistic interactions between the internal structure of scene and EM wavefield are taken into account in the imaging…

Conventional deep learning-based image reconstruction methods require a large amount of training data which can be hard to obtain in practice. Untrained deep learning methods overcome this limitation by training a network to invert a…

We propose a new method to probe the learning mechanism of Deep Neural Networks (DNN) by perturbing the system using Noise Injection Nodes (NINs). These nodes inject uncorrelated noise via additional optimizable weights to existing…

Preliminary results from H1 and ZEUS on Deep Inelastic Scattering (DIS) at high momentum transfer squared $Q^2$ are presented. Used are all available $e^+ p$ data accumulated by the H1 and ZEUS experiments between 1994 and 1997,…

A very wide body of HERA diffractive electroproduction data is confronted with the predictions of the colour dipole model. In doing so we focus upon three different parameterisations of the dipole scattering cross-section, whose parameters…

Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received,…

The large center of mass energy and increasing statistical precision for a wide range of hadronic final state observables at the HERA lepton-proton collider has provided a detailed testing ground for QCD dynamics. Fully flexible…

In hadrons and nuclei at very small x, parton distributions saturate at a scale Q_s(x). Since the occupation number is large, and $Q_s(x)>>\Lambda_{QCD}$, classical weak coupling methods may be used to study this novel regime of non-linear…

The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep…

Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…

A methodology based on deep recurrent models for maritime surveillance, over publicly available Automatic Identification System (AIS) data, is presented in this paper. The setup employs a deep Recurrent Neural Network (RNN)-based model, for…

The results from a recent analysis on beauty production in deep inelastic scattering at HERA using decays into electrons from the ZEUS collaboration are presented. The fractions of events containing b quarks were extracted from a likelihood…

21-cm intensity mapping (IM) is a powerful technique to probe the large-scale distribution of neutral hydrogen (HI) and extract cosmological information such as the baryon acoustic oscillation feature. A key challenge lies in recovering the…

Incorporating a priori physics knowledge into machine learning leads to more robust and interpretable algorithms. In this work, we combine deep learning techniques and classic numerical methods for differential equations to address two…