Fig. 3From: A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizureFeature extraction model composed of convolutional layers followed by max pool and dropout. The convolutional layers are distributed: 2 of 32, 2 of 64, 3 of 128, 3 of 256, and finally, 9 of 512 divided into blocks of 3Back to article page