1. Performance of the Levenberg–Marquardt neural network approach in nuclear mass prediction
- Author
-
Hong-Fei Zhang, Li Hao Wang, Peng Hui Chen, H. F. Zhang, and Jing Peng Yin
- Subjects
Physics ,Root mean square ,Levenberg–Marquardt algorithm ,Nuclear and High Energy Physics ,Artificial neural network ,Semi-empirical mass formula ,010308 nuclear & particles physics ,0103 physical sciences ,Liquid drop ,010306 general physics ,01 natural sciences ,Algorithm ,Atomic mass - Abstract
Resorting to a neural network approach we refined several representative and sophisticated global nuclear mass models within the latest atomic mass evaluation (AME2012). In the training process, a quite robust algorithm named the Levenberg–Marquardt (LM) method is employed to determine the weights and biases of the neural network. As a result, this LM neural network approach demonstrates a very useful tool for further improving the accuracy of mass models. For a simple liquid drop formula the root mean square (rms) deviation between the predictions and the 2353 experimental known masses are sharply reduced from 2.455 MeV to 0.235 MeV, and for the other revisited mass models, the rms is remarkably improved by about 30%.
- Published
- 2017