How to classify MNIST digits with different neural network architectures

I took a Deep Learning course through The Bradfield School of Computer Science in June. This series is a journal about what I learned in class, and what I've learned since. This is the third article in the series. You can find the first article in the series here, and the second article in the series here. Please note: All of the code samples below can be found and run in this Jupyter Notebook kindly hosted by Google Colaboratory. I encourage you to copy the code, make changes, and experiment with the networks yourself as you read this article. Although neural networks have gained enormous popularity over the last few years, for many data scientists and statisticians the whole family of models has (at least) one major flaw: the results are hard to interpret.