Supervised learning

Machine learning that learns patterns from data humans have already labelled, then makes decisions on new data. The phone face-recognition setup is a clean example: tilting your face labels each frame, and the phone uses that labelled data to recognise you later.

Most medical AI you've met is supervised learning. Radiologists labeled tens of thousands of images as "cancer" or "not cancer," and the model learned to copy those labels on new scans. The catch sits in the labels: if the training images came from one scanner at one hospital, the model learned that hospital's habits, not the disease. This is why a tool that works in the published study can fail on your equipment.

Terms like this come up in real clinical scenarios across the HelloAI courses: bite-sized modules with verifiable certificates. An account takes one minute, no password needed.