Generative Deep Learning, 2nd Edition

Chapter 2. Deep Learning

Chapter Goals

In this chapter you will:

• Learn about the different types of unstructured data that can be modeled using deep learning.

• Define a deep neural network and understand how it can be used to model complex datasets.

• Build a multilayer perceptron to predict the content of an image.

• Improve the performance of the model by using convolutional layers, dropout, and batch normalization layers.

Let’s start with a basic definition of deep learning:

Deep learning is a class of machine learning algorithms that uses multiple stacked layers of processing units to learn high-level representations from unstructured data.

To understand deep learning fully, we need to delve into this definition a bit further. First, we’ll take a look at the different types of unstructured data that deep learning can be used to model, then we’ll dive into the mechanics of building multiple stacked layers of processing units to solve classification tasks. This will provide the foundation for future chapters where we focus on deep learning for generative tasks.

Data for Deep Learning

Many types of machine learning algorithms require structured, tabular data as input, arranged into columns of features that describe each observation. For example, a person’s age, income, and number of website visits in the last month are all features that could help to predict if the person will subscribe to a particular online service in the coming month. We could use a structured table ...