Related papers: Bayesian neural network with autoencoder for model…

Building on the work of E. L. Medeiros [1] and our previous study [2], we generalize the alpha-nucleus nonlocality effect to odd-A and odd-odd nuclei within the two-potential approach (TPA) framework. The coordinate-dependent parameters…

This paper addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring…

Tensor Network (TN) Kernel Machines speed up model learning by representing parameters as low-rank TNs, reducing computation and memory use. However, most TN-based Kernel methods are deterministic and ignore parameter uncertainty. Further,…

The existence of long lived superheavy nuclei (SHN) is controlled mainly by spontaneous fission and $\alpha$-decay processes. According to microscopic nuclear theory, spherical shell effects at Z=114, 120, 126 and N=184 provide the extra…

The willingness to trust predictions formulated by automatic algorithms is key in a vast number of domains. However, a vast number of deep architectures are only able to formulate predictions without an associated uncertainty. In this…

Bayesian regularization-backpropagation neural network (BR-BPNN) model is employed to predict some aspects of the gecko spatula peeling viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at…

We exploit the great potential offered by Bayesian Neural Networks (BNNs) to directly decipher the internal composition of neutron stars (NSs) based on their macroscopic properties. By analyzing a set of simulated observations, namely NS…

Intensive research has been conducted on the verification and validation of deep neural networks (DNNs), aiming to understand if, and how, DNNs can be applied to safety critical applications. However, existing verification and validation…

The recently observed $\alpha$-decay chain ${}^{108}\text{Xe}\to{}^{104}\text{Te}\to{}^{100}\text{Sn}$ [K.~Auranen \emph{et al.}, Phys.\ Rev.\ Lett.\ {\bf121}, 182501 (2018)] could provide valuable information on the $\alpha$ clustering in…

In this work, we have analyzed the nuclear structure and several prospective decay characteristics of the $^{240-259}$Es$_{99}$ isotopes. For this we use Relativistic Mean Field model (RMF) with NL-SH and NL3* force parameter in an axially…

We build random forests models to predict elastic properties and mechanical hardness of a compound, using only its chemical formula as input. The model training uses over 10,000 target compounds and 60 features based on stoichiometric…

Context. Ongoing and upcoming large spectroscopic surveys are drastically increasing the number of observed quasar spectra, requiring the development of fast and accurate automated methods to estimate spectral continua. Aims. This study…

Autoencoders are among the earliest introduced nonlinear models for unsupervised learning. Although they are widely adopted beyond research, it has been a longstanding open problem to understand mathematically the feature extraction…

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is…

The robust estimation of dynamically changing features, such as the position of prey, is one of the hallmarks of perception. On an abstract, algorithmic level, nonlinear Bayesian filtering, i.e. the estimation of temporally changing signals…

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

The large-scale shell-model calculations have been performed for the neutron-rich nuclei in the south region of $^{208}$Pb in the nuclear chart. The $\beta$-decay properties, such as the $\log ft$, average shape factor values, half-lives,…

Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fractions (abundances),…

We evaluate the allowed $\beta^-$-decay properties of nuclei with $Z = 8 - 15$ systematically under the framework of the nuclear shell model with the use of the valence space Hamiltonians derived from modern $ab~intio$ methods, such as…

Beta-decay rates of extreme neutron-rich nuclei remain largely unknown experimentally, while they are critical inputs for $r$-process nucleosynthesis. We present first ab initio calculations of total beta-decay half-lives, with a focus on…