Nuclear mass predictions based on deep neural network and finite-range droplet model (2012)

Abstract

A neural network with two hidden layers is developed for nuclear mass prediction, based on the finite-range droplet model (FRDM12). Different hyperparameters, including the number of hidden units, the choice of activation functions, the initializers, and the learning rates, are adjusted explicitly and systematically. The resulting mass predictions are achieved by averaging the predictions given by several different sets of hyperparameters with different regularizers and seed numbers. It can provide us not only the average values of mass predictions but also reliable estimations in the mass prediction uncertainties. The overall root-mean-square deviations of nuclear mass have been reduced from $0.603$ MeV for the FRDM12 model to $0.200$ MeV and $0.232$ MeV for the training set and validation set, respectively.

12 pages, 12 figures, and 1 table

References in corpus (7)

• New parametrization for the nuclear covariant energy density functional with point-coupling interaction
• Surface diffuseness correction in global mass formula
• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• Machine learning and density functional theory
• Nuclear mass predictions with machine learning reaching the accuracy required by $r$-process studies
• Nuclear masses in extended kernel ridge regression with odd-even effects
• Application Of Support Vector Machines To Global Prediction Of Nuclear Properties

Cited by in corpus (1)

• Further exploration of the machine-learning-based nuclear mass table