What You Just Learned

In this chapter we got up close and personal with MNIST. We wrote a little library to import MNIST data and reshape it to X and Y matrices fit for our binary classification code. In the end, we used our program to recognize one of the digits in MNIST, with very encouraging results.

Along the way, you learned a few interesting facts about image recognition. You also learned something about testing ML systems, and how the results of a test can be tricky to interpret because of overfitting.

In the next chapter, we’ll finally tackle the challenge that we set for ourselves at the beginning of this book: recognizing arbitrary digits. How will our code fare?