Fig. 5
From: Detecting epileptic seizures with electroencephalogram via a context-learning model
The structure of an autoencoder. x is the input data, h is the hidden unit and +1 term is adopted to integrate the bias. It is composed of two parts, an encoder and a decoder. The output of the encoder is the extracted features for the input data and the decoder is tuned to reconstruct the input data based on the extracted features