Fusion of Deep Features from 2D-DOST of fNIRS Signals for Subject-Independent Classification of Motor Execution Tasks

Table 2

Parameters used for training.

Parameter	Value
Learning rate	0.001
Regularization parameter	0.002
Maximum number of epochs	100
Batch size	64
Momentum	0.85
Learning rate drop factor	0.2
Learning rate drop period	20
Optimizer	Stochastic gradient descent with momentum (SGDM)
Loss function	Cross-entropy