Fig. 4.
Differential bidirectional LSTM model for sleep episode onset/offset estimation. The input xt is the feature vector at time t, and , are the estimated sleep episode onset/offset probabilities. Output dimensions are denoted in each box.
Differential bidirectional LSTM model for sleep episode onset/offset estimation. The input xt is the feature vector at time t, and , are the estimated sleep episode onset/offset probabilities. Output dimensions are denoted in each box.