Introduction

A. Multilayer perceptron

A multilayer perceptron (MLP) is used for a variety of tasks, such as stock analysis, spam detection, and election voting predictions. In this chapter and the next one, you'll learn how to code your own MLP and apply it to the task of classifying 2-D points in the Cartesian plane.

You'll also learn the basics of creating a computation graph—the structure of a neural network. The structure of a neural network can be viewed in layers of neurons:

In the diagram, the circles represent neurons and the connections are the arrows going from neurons in one layer to the next. There are three layers in this diagram's neural network:

• Input layer: The first (bottom) layer.
• Output layer: The last (top) layer.
• Hidden layer(s): The layer(s) between the input and output layers. In the diagram, there is 1.

When diagramming the computation graph, it is common to eschew the neurons and connections:

This makes it easier to view computation graphs of complex neural networks with dozens of layers.

B. TensorFlow

To code our neural network model, we will be using TensorFlow, one of the most popular deep learning frameworks. The name for TensorFlow is derived from tensors, which are basically multidimensional (i.e. generalized) vectors/matrices. When writing the code, it may be easier to think of anything with numeric values as being a tensor.

In TensorFlow, we first create the computation graph structure and then train and evaluate the model with input data and labels.

A quick note: TensorFlow is normally imported via the statement import tensorflow as tf. This provides a shorthand way to call the module.