In this chapter, we will build a simple multilayer perceptron (MLP), which is a fancy name for a neural network with a single hidden layer, to solve a regression problem. Then we will go deeper with a deep neural network that has several hidden layers. Along the way, we will explore model performance and over fitting. So, let's get started!

We will cover the following topics in this chapter:

• Regression analysis and deep neural networks
• Using deep neural networks for regression
• Building an MLP in Keras
• Building a deep neural network in Keras
• Saving and loading a trained Keras model