Soon enough, we’ll get to tune our neural network and make it as accurate as we can. Before we do that, however, we need a reliable test to measure that accuracy. As it turns out, ML testing comes with a subtly counterintuitive hurdle that can easily trip you up.
It’s hard to explain that hurdle in a few lines—so give me a few pages instead. This short chapter tells you where that testing trapdoor is, and how to step around it.