Using deep neural networks for regression

Now that you hopefully understand why you would (and would not) want to use deep neural networks for regression, I'll show you how to do it. While it's not quite as simple as using linear regressor in scikit-learn, I think you'll find it quite easy using Keras. Most importantly, Keras will allow you to quickly iterate through model architectures without changing a lot of code.

How to plan a machine learning problem

When building a new neural network, I recommend following the same basic steps every time. 

Note

Deep neural networks can get very complicated, very quickly. A little bit of planning and organization and greatly accelerate your workflow!

The following are the steps for building a deep neural network:

1. Outline the problem you're trying to solve.
2. Identify the inputs and outputs of the model.
3. Choose a cost function and metrics.
4. Create an initial network architecture.
5. Train and tune the network.

Defining our example problem

In our example problem, we will...