Speaker
Dr
Isaac Vidana
(Istituto Nazionale di Fisica Nuclare (INFN))
Description
We employ a feed-forward artificial neural network (ANN) to extrapolate, at large model spaces, the hypernuclear No-Core Shell Model results of Refs. Few-Body Syst, 55 (2014) 857 and Few-Body Syst. 62 (2021) 94 for the $\Lambda$ separation energies of the lightest hypernuclei, $^3_\Lambda$H, $^4_\Lambda$H and $^4_\Lambda$He, obtained with chiral nucleon-nucleon and hyperon-nucleon potentials.
We find that an ANN with a single hidden layer of eight neurons is sufficient to extrapolate correctly the $\Lambda$ separation energies of the three hypernuclei considered. This is in agreement with the universal approximation theorem which assures that any continuous function can be realized by a network with just one hidden layer.
Primary author
Dr
Isaac Vidana
(Istituto Nazionale di Fisica Nuclare (INFN))
