Quantifying uncertainty in machine learning for nuclear binding energy

Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory; however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked. Epistemic uncertainties arising from training the same network multiple times for an ensemble of initial weight sets offer a first insight into the confidence of machine learning predictions, but they often come with a high computational cost. Instead, we apply a single-model uncertainty quantification method called Δ-UQ that gives epistemic uncertainties with one-time training. Here, we demonstrate our approach on a two-feature model of nuclear binding energies per nucleon with proton and neutron number pairs as inputs. We show that Δ-UQ can produce reliable and self-consistent epistemic uncertainty estimates and can be used to assess the degree of confidence in predictions made with deep neural networks.. Authors: Huang, Mengyao [Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)] (ORCID:0000000306892081); Wendt, Kyle A. [Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)] (ORCID:0000000234286479); Schunck, Nicolas F. [Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)] (ORCID:0000000292036849); Holmbeck, Erika M. [Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)] (ORCID:0000000254636800). DOE Contract: AC52-07NA27344