More than one. Graduation thesis through the network needs to use a variety of modes to achieve different tasks and goals. Regression model can be used to predict continuous value output. Commonly used regression models include fully connected neural network (FFN), multilayer perceptron (MLP) and linear regression model. The classification model can be used to classify and predict the input data. Commonly used classification models include convolutional neural network (CNN), recurrent neural network (RNN) and long-term memory network (LSTM).