Figure 5.
Network architecture for real-value prediction of backbone torsion angles (SPINE XI). Two sets of neural networks are constructed for predicting angle peaks (Peak I or Peak II) by a two-state classifier (A1–A5) and the deviation from the peak by a real-value predictor (B1–B5). Both predictions result from a consensus of five independent predictions. Each predictor (A1,..A5,B1,…B5) has two hidden layers. Angles predicted by neural networks are further refined by the conditional random field (CRF) model.
