Sequential Models

A sequential model is used to build regression and classification models. In sequential models, information propagates through the network from the input layer at the beginning to the output layer at the end. Layers are stacked in the model sequentially, with each layer having an input and an output.

Other types of ANN models exist, such as recurrent neural networks (in which the output feeds back into the input), which will be covered in later chapters. The difference between sequential and recurrent neural networks is shown in Figure 4.01. In both the models, the information flows from the input layer through the hidden layers to the output layer, as indicated by the direction of the arrows. However, in recurrent architectures, the output of the hidden layers feeds back into the input of the hidden layers:

Figure 4.1: The architectures of sequential and recurrent ANNs

In the following section, you will learn how to create sequential models...