Deep Learning for Coders with fastai and PyTorch

Chapter 4. Under the Hood: Training a Digit Classifier

Having seen what it looks like to train a variety of models in Chapter 2, let’s now look under the hood and see exactly what is going on. We’ll start by using computer vision to introduce fundamental tools and concepts for deep learning.

To be exact, we’ll discuss the roles of arrays and tensors and of broadcasting, a powerful technique for using them expressively. We’ll explain stochastic gradient descent (SGD), the mechanism for learning by updating weights automatically. We’ll discuss the choice of a loss function for our basic classification task, and the role of mini-batches. We’ll also describe the math that a basic neural network is doing. Finally, we’ll put all these pieces together.

In future chapters, we’ll do deep dives into other applications as well, and see how these concepts and tools generalize. But this chapter is about laying foundation stones. To be frank, that also makes this one of the hardest chapters, because of how these concepts all depend on each other. Like an arch, all the stones need to be in place for the structure to stay up. Also like an arch, once that happens, it’s a powerful structure that can support other things. But it requires some patience to assemble.

Let’s begin. The first step is to consider how images are represented in a computer.

Pixels: The Foundations of Computer Vision

To understand what happens in a computer vision model, we first have to understand how computers handle images. ...