Learning Data Mining with Python - Second Edition

An introduction to neural networks

For data mining applications, the arrangement of neurons is usually in layers. The first layer is called the input layer and takes its input from samples in the data. The outputs of each of these neurons are computed and then passed along to the neurons in the next layer. This is called a feed-forward neural network. We will refer to these simply as neural networks for this chapter, as they are the most common type used and the only type used in this chapter. There are other types of neural networks too that are used for different applications. We will see another type of network in Chapter 11, Object Detection in Images Using Deep Neural Networks.

The outputs of one layer become the inputs of the next layer, ...