When you think about deep learning, you probably think about impressively complex computer vision problems, but deep neural networks can prove useful even for simple regression problems like this one. Hopefully, I've demonstrated that, while also introducing the Keras syntax and showing you how to build a very simple network.

As we continue, we will encounter much more complexity. Bigger networks, more complicated cost functions, and highly dimensional input data. However, the process I used in this chapter will remain same for the most part. In each case, we will outline the problem, identify the inputs and outputs, choose a cost function, create a network architecture, and finally train and tune our model. 

Bias and variance can often be manipulated and reduced independently in deep neural networks if the following factors are taken care of:

• Bias: This can be reduced by adding model complexity. Additional neurons or layers will help. Adding data won't really help reduce bias.
• Variance: This can be reduced by adding data or regularization.

In the next chapter, we will talk about how we can use TensorBoard to optimize and troubleshoot our deep neural networks faster.