Related papers: Taming nucleon density distributions with deep neu…

A deep neural network (DNN) has been developed to generate the distributions of nuclear charge density, utilizing the training data from the relativistic density functional theory and incorporating available experimental charge radii of…

A deep neural network (DNN) has been developed to accurately predict nuclear charge density distributions for nuclei with proton numbers $Z \geq 8$. By incorporating essential nuclear structure features, the model achieves a significant…

A Kohn-Sham scheme based multi-task neural network is elaborated for the supervised learning of nuclear shell evolution. The training set is composed of the single-particle wave functions and occupation probabilities of 320 nuclei,…

Proton and neutron density profiles of 760 nuclei in the mass region of A=16-304are analyzed using the Skyrme energy density for the parameter set SLy4. Simple formulae are obtained to fit the resulting radii and diffuseness data. These…

Over the past decade, machine learning has been successfully applied in various fields of science. In this study, we employ a deep learning method to analyze a Skyrme energy density functional (Skyrme-EDF), that is a Kohn-Sham type…

We employed the Skyrme-Hartree-Fock model to investigate the density distributions and their dependence on nuclear shapes and isospins in the superheavy mass region. Different Skyrme forces were used for the calculations with a special…

The nuclear charge density distribution plays an important role in nuclear physics and atomic physics. As one of the most frequently used models to obtain charge density distribution, the two-parameter fermi (2pF) model has been widely…

We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The…

Parameters of the nuclear density functional theory (DFT) models are usually adjusted to experimental data. As a result they carry certain theoretical error, which, as a consequence, carries out to the predicted quantities. In this work we…

Uncertainties in nuclear models have a major impact on simulations that aim at understanding the origin of heavy elements in the universe through the rapid neutron capture process ($r$ process) of nucleosynthesis. Within the framework of…

Based on the relativistic impulse approximation of proton-nucleus elastic scattering theory, the nucleon density distribution and neutron skin thickness of $^{48}$Ca are estimated via the deep learning method. The neural-network-generated…

The nuclear binding energies for 28 nuclei including several isotopic chains with masses ranging from A=64 to A=226 were evaluated using the Skyrme effective nucleon-nucleon interaction and the Extended Thomas-Fermi approximation. The…

The Skyrme nuclear energy density functional theory (DFT) is used to model neutron-induced fission in actinides. This paper focuses on the numerical implementation of the theory. In particular, it reports recent advances in DFT code…

Recent work has focused on combining kernel methods and deep learning to exploit the best of the two approaches. Here, we introduce a new architecture of neural networks in which we replace the top dense layers of standard convolutional…

A deep convolutional neural network (CNN) is developed to study symmetry energy $E_{\rm sym}(\rho)$ effects by learning the mapping between the symmetry energy and the two-dimensional (transverse momentum and rapidity) distributions of…

We demonstrate that the matter density distribution in the surface region is determined well by the use of the relatively low-intensity beams that become available at the upcoming radioactive beam facilities. Following the method used in…

In this paper, we aim at establishing an approximation theory and a learning theory of distribution regression via a fully connected neural network (FNN). In contrast to the classical regression methods, the input variables of distribution…

Although the neural network (NN) technique plays an important role in machine learning, understanding the mechanism of NN models and the transparency of deep learning still require more basic research. In this study, we propose a novel…

Recent analysis of the isospin diffusion data from heavy-ion collisions based on an isospin- and momentum-dependent transport model with in-medium nucleon-nucleon cross sections has led to the extraction of a value of $L=88\pm 25$ MeV for…

Although neural networks are routinely and successfully trained in practice using simple gradient-based methods, most existing theoretical results are negative, showing that learning such networks is difficult, in a worst-case sense over…