For the SGA architecture used in this paper [57], the basic
GA remains unchanged except that fitness evaluations are
obtained from a forward pass of the genome through a neural
network when the real fitness value is unknown. Initially the
entire population is fabricated and evaluated on the real fitness
function and added to an evaluated set. The model is trained
using backpropagation for 1000 epochs; where an epoch consists
of randomly selecting, without replacement, an individual
from the evaluated set and updating the model weights. Each
generation thereafter, the individual with the highest approximated
fitness as suggested by the model and a randomly
chosen unevaluated individual are fabricated and evaluated on
the real fitness function and added to the evaluated set, whereupon
the model is iteratively retrained. The model parameters
are β = 0.3, θ = 0, elasticity = 1, calming rate = 1,
momentum = 0, elasticity rate = 0.