Table 5.

Overview of the different neural network parameters used.

Parameter	Value	Description
Network
num layers	4	Number of hidden neural network layers
num nodes	150	Number of nodes per hidden neural network layer
$N$	32	Batch size
$c$	100	Maximum norm for clip gradient
$T_0$	0s	Used for scaling of $t$
$T_1$	50s	Used for scaling of $t$
Learning Rate
$\eta$	0.001	Learning rate
reduction factor	0.5
patience	5000
min lr	1e-6	Minimal learning rate