Backflow Transformation for A=3 Nuclei with Artificial Neural Networks

A novel variational wave function defined as a Jastrow factor multiplying a backflow transformed Slater determinant was developed for A=3 nuclei. The Jastrow factor and backflow transformation were represented by artificial neural networks. With this newly developed wave function, variational Monte Carlo calculations were carried out for ³H and ³He nuclei starting from a nuclear Hamiltonian based on the leading-order pionless effective field theory. The obtained ground-state energy and charge radii were successfully benchmarked against the results of the highly-accurate hyperspherical-harmonics method. The backflow transformation plays a crucial role in improving the nodal surface of the Slater determinant and, thus, providing accurate ground-state energy.