Table 2.

Selected inter-subject hyperparameters (CNNs).

	Shallow CNN		Deep CNN		EEGNet
	Words	Vowels	Words	Vowels	Words	Vowels
Activation Function	leaky ReLU	leaky ReLU	leaky ReLU	leaky ReLU	ELU	ELU
Learning Rate	0.1	0.1	0.1	0.1	1	1
Epochs	60	60	60	60	80	80
Loss	CE	NLL	CE	CE	NLL	NLL