10.11.2016 Views

Learning Data Mining with Python

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Chapter 8<br />

The red lines indicate that the value is 0.5 when x is zero.<br />

Each individual neuron receives its inputs and then computes the output based<br />

on these values. Neural networks are simply networks of these neurons connected<br />

together, and they can be very powerful for data mining applications. The<br />

combinations of these neurons, how they fit together, and how they combine<br />

to learn a model are one of the most powerful concepts in machine learning.<br />

An introduction to neural networks<br />

For data mining applications, the arrangement of neurons is usually in layers. The<br />

first layer, the input layer, takes the inputs from the dataset. The outputs of each<br />

of these neurons are computed and then passed along to the neurons in the next<br />

layer. This is called a feed-forward neural network. We will refer to these simply<br />

as neural networks for this chapter. There are other types of neural networks too<br />

that are used for different applications. We will see another type of network in<br />

Chapter 11, Classifying Objects in Images Using Deep <strong>Learning</strong>.<br />

[ 163 ]

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!