Monte Carlo dropout Bayesian neural network trained with physics inputs reproduces abrupt charge-radii increase near N=60 for Z=37-40 and shell quenching at N=126, achieving comparable RMSD on training and validation sets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Radioactive molecules combine nuclear and molecular properties to offer enhanced sensitivity for detecting new physics beyond the Standard Model.
citing papers explorer
-
Input-driven analysis in predicting nuclear charge radii using Monte Carlo dropout Bayesian neural network
Monte Carlo dropout Bayesian neural network trained with physics inputs reproduces abrupt charge-radii increase near N=60 for Z=37-40 and shell quenching at N=126, achieving comparable RMSD on training and validation sets.
-
Radioactive Molecules as Laboratories of Fundamental Physics
Radioactive molecules combine nuclear and molecular properties to offer enhanced sensitivity for detecting new physics beyond the Standard Model.