AI Literacy / Glossary

Machine learning

Machine learning is the main way AI is built today: a computer is shown many examples, finds the patterns in them, and uses those patterns to handle new cases it has never seen.

Instead of writing a rule like "an email with these words is spam", developers give the system thousands of emails already marked spam or not spam. The system adjusts itself until it sorts them well, and the result is called a model.

The model is then tested on examples it did not see during training. If the training examples were varied and fair, it usually works well on new cases. If they were narrow or skewed, it fails in ways that are easy to miss.

Machine learning powers recommendations, translation, image recognition and chatbots. It finds patterns; it does not understand meaning or check facts the way a person does.