Let's go back to our dog classifier. There are in fact many such classifiers currently in use today. If you use Google images, for example, and search for "dog," it will use an image classifier to show you pictures of dogs. These classifiers are trained under a paradigm known as supervised learning.

Supervised learning

In supervised learning, we have a large number of training examples, such as images of animals, and labels that describe what the expected outcome for those training examples is. For example, the preceding figure would come with the label "dog," while an image of a cat would come with a label "not a dog."

If we have a high number of these labeled training examples, we can train a classifier on detecting the subtle statistical patterns that differentiate dogs from all other animals.

If a supervised learning classifier encounters something that's very different from the training data, it can often get confused and will just output nonsense.