Table 1 Parameters set for EEGNet architecture according to original paper50.

From: Recurrent and convolutional neural networks in classification of EEG signal for guided imagery and mental workload detection

Parameter

Description

Value

F1

Number of temporal filters

8

F2

Number of pointwise filters

16

k

Kernel length

125

D

Number of spatial filters for each temporal convolution

2 (original value)

–

Activation function in output layer

Sigmoid

Back to article page