Solving quantum many-body problems with a Neural Quantum State was first proposed in . This package implements parallel sampling and optimization of many-body wavefunctions of arbitrary Hamiltonians.
 Carleo, Giuseppe, and Matthias Troyer. "Solving the quantum many-body problem with artificial neural networks." Science 355.6325 (2017): 602-606.
] in the REPL and simply add the package by typing:
(v1.X) pkg> add NeuralQuantumState
julia > using Distributed julia > addprocs(2) # Add no. of desired worker processes. julia > @everywhere using Random julia > @everywhere using NeuralQuantumState julia > @sync for i in workers() @async remotecall_wait(Random.seed!, i, i * 99999) end julia > NetSettings = NETSETTINGS( modelname = "U_afh", # Marshall transformed AFH. repetitions =1000, n = 6, α = 3, mag0 = true, γ_decay = 0.997, mc_trials = 500, writetofile=true, init_therm_steps = 100, therm_steps = 50, stat_samples = 2000) julia > energy = run_NQS(NetSettings)
The author of this package is not affiliated with the authors of the original publication. See NetKet for the official C++ implementation.