Related papers: Bayesian neural network with autoencoder for model…
We present a microscopic model for the calculation of alpha-decay half lives employing potentials obtained from relativistic and non-relativistic self-consistent mean-field models. The nuclear and Coulomb potentials are used to obtain the…
In recent years, several successful applications of the Artificial Neural Networks (ANNs) have emerged in nuclear physics and high-energy physics, as well as in biology, chemistry, meteorology, and other fields of science. A major goal of…
The interaction potential between the alpha particle and the deformed parent nucleus was used for description of the decay of superheavy nuclei. It consists of centrifugal, nuclear and Coulomb parts suitably modified for deformed nuclei.…
We introduce a new method, called CNNAS (convolutional neural networks for atomistic systems), for calculating the total energy of atomic systems which rivals the computational cost of empirical potentials while maintaining the accuracy of…
Solving partial differential equations (PDEs) is the canonical approach for understanding the behavior of physical systems. However, large scale solutions of PDEs using state of the art discretization techniques remains an expensive…
In recent years, deep learning has proven to be a viable methodology for surrogate modeling and uncertainty quantification for a vast number of physical systems. However, in their traditional form, such models can require a large amount of…
Bayesian Neural Networks (BNNs) offer a principled and natural framework for proper uncertainty quantification in the context of deep learning. They address the typical challenges associated with conventional deep learning methods, such as…
Superheavy nuclei represent the heaviest atoms and nuclides known at the limit of mass and charge. The observed superheavy nuclei are all proton-rich; they decay primarily by emitting $\alpha$ particles and fission, with a possible small…
Different models for the nonlocal description of the nuclear interaction are compared through a study of their effects on the half-lives of radioactive nuclei decaying by the emission of alpha particles. The half-lives are evaluated by…
Uncertainty in biological neural systems appears to be computationally beneficial rather than detrimental. However, in neuromorphic computing systems, device variability often limits performance, including accuracy and efficiency. In this…
The $\beta$-decay properties of nuclei with neutron number $N = 126$ is investigated in this paper. Two different versions of the proton-neutron quasi particle random phase (pn-QRPA) model were employed to compute $\beta$-decay rates and…
We report microscopic calculation of key $\beta$-decay properties for some of the crucial waiting point species having neutron closed magic shells 50 and 82. Our calculation bear astrophysical significance vis-\'{a}-vis speeding of the…
[Background] $\beta$-decay half-life is sensitive to the shell structure near the Fermi levels. Nuclear deformation thus impacts the $\beta$-decay properties. [Purpose] A first-order shape-phase transition in neutron-rich Zr isotopes is…
Theoretical estimates for the lifetimes of several isotopes of heavy elements with Z=102-120 are presented by calculating the quantum mechanical tunneling probability in a WKB framework and using microscopic nucleus-nucleus potential…
Radioactive decay of nuclei via emission of $\alpha$ particles has been studied theoretically in the framework of a superasymmetric fission model using the double folding (DF) procedure for obtaining the $\alpha$-nucleus interaction…
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…
The alpha-decay half-lives and the alpha-capture cross-sections are evaluated in the framework of unified model for alpha-decay and alpha-capture. In the framework of this model the alpha-decay and alpha-capture are considered as…
Active learning optimizes the exploration of large parameter spaces by strategically selecting which experiments or simulations to conduct, thus reducing resource consumption and potentially accelerating scientific discovery. A key…
We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences,…
Uncertainty quantification is an important task in machine learning - a task in which standardneural networks (NNs) have traditionally not excelled. This can be a limitation for safety-critical applications, where uncertainty-aware methods…