Related papers: Bayesian Learning of (n,p) Reaction Cross Sections…
Modern nuclear data evaluation increasingly requires not only accurate scattering calculations, but also efficient methods for uncertainty quantification and parameter optimization, tasks that benefit from differentiable solvers amenable to…
Ensembles of neural networks (NNs) have long been used to estimate predictive uncertainty; a small number of NNs are trained from different initialisations and sometimes on differing versions of the dataset. The variance of the ensemble's…
Quantifying the uncertainty in the output of a neural network is essential for deployment in scientific or engineering applications where decisions must be made under limited or noisy data. Bayesian neural networks (BNNs) provide a…
We discuss nuclear reactions which could play a role in Big Bang Nucleosynthesis (BBN). Most of these reactions involve lithium and beryllium isotopes and the rates for some of these have not previously been included in BBN calculations.…
In nuclear astrophysics, the accurate determination of nuclear reaction cross sections at astrophysical energies is critical for understanding stellar evolution and nucleosynthesis. This study focuses on the $^{12}$C($p, \gamma$)$^{13}$N…
In several processes of stellar nucleosynthesis, like the astrophysical gamma-process, nuclear reactions involving alpha particles play an important role. The description of these reactions necessitates the knowledge of the alpha-nucleus…
Understanding the radiogenic neutron production rate through the (${\alpha}$, n) reaction is crucial in many areas of physics, including dark matter searches, neutrino studies, and nuclear astrophysics. In addition to its relevance for…
We present a physics-informed Bayesian neural-network framework to infer neutron-star equations of state from theoretical priors and to propagate the associated uncertainties to stellar observables. Trained on a large and representative…
Nuclear structure theory can provide nuclear astrophysics and nuclear technologies with bound state properties and transition rates. When describing nuclear reactions, the list can be extended to include statistical properties such as…
The methods used in the evaluation of the neutrino-nucleus cross section are reviewed. Results are shown for a variety of targets of practical importance. Many of the described reactions are accessible in future experiments with neutrino…
Neural networks (NNs) are primarily developed within the frequentist statistical framework. Nevertheless, frequentist NNs lack the capability to provide uncertainties in the predictions, and hence their robustness can not be adequately…
Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs,…
An IAEA research project was dedicated to the compilation, evaluation and recommendation of cross-section data for the accelerator production of $^{11}$C, $^{13}$N, $^{15}$O, $^{18}$F, $^{64}$Cu, and $^{124}$I positron-emitting…
Principled Bayesian deep learning (BDL) does not live up to its potential when we only focus on marginal predictive distributions (marginal predictives). Recent works have highlighted the importance of joint predictives for (Bayesian)…
Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to…
A microscopic description of the interaction of atomic nuclei with external electroweak probes is required for elucidating aspects of short-range nuclear dynamics and for the correct interpretation of neutrino oscillation experiments.…
This paper investigates two prominent probabilistic neural modeling paradigms: Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression. While BNNs incorporate epistemic uncertainty by…
Neural network potentials (NNPs) combine the computational efficiency of classical interatomic potentials with the high accuracy and flexibility of the ab initio methods used to create the training set, but can also result in unphysical…
We propose a Bayesian physics-informed neural network (B-PINN) to solve both forward and inverse nonlinear problems described by partial differential equations (PDEs) and noisy data. In this Bayesian framework, the Bayesian neural network…
Ab-initio calculations of nuclear masses, the binding energy and the $\alpha$ decay half-lives are intractable for heavy nucleus, because of the curse of dimensionality in many body quantum simulations as proton number($\mathrm{N}$) and…