Machine learning light hypernuclei
Abstract
We employ a feed-forward artificial neural network to extrapolate at large model spaces the results of {\it ab-initio} hypernuclear No-Core Shell Model calculations for the separation energy of the lightest hypernuclei, H, H and He, obtained in computationally accessible harmonic oscillator basis spaces using chiral nucleon-nucleon, nucleon-nucleon-nucleon and hyperon-nucleon interactions. The overfitting problem is avoided by enlarging the size of the input dataset and by introducing a Gaussian noise during the training process of the neural network. We find that a network with a single hidden layer of eight neurons is sufficient to extrapolate correctly the value of the separation energy to model spaces of size . The results obtained are in agreement with the experimental data in the case of H and the state of He, although they are off of the experiment by about MeV for both the and states of H and the state of He. We find that our results are in excellent agreement with those obtained using other extrapolation schemes of the No-Core Shell Model calculations, showing this that an ANN is a reliable method to extrapolate the results of hypernuclear No-Core Shell Model calculations to large model spaces.
Cite
@article{arxiv.2203.11792,
title = {Machine learning light hypernuclei},
author = {Isaac Vidana},
journal= {arXiv preprint arXiv:2203.11792},
year = {2023}
}
Comments
16 pages, 7 figures, 1 table. Accepted for publication in Nuclear Physics A