In this lesson
- It starts with a question. How does a program learn to tell ripe mangoes from unripe ones in photographs?
- The idea you will find. The model learns the data, not the truth. — If every ripe mango in the training photos was shot on a blue table, the model may learn "blue table" and fail in a field. This is why the quality and spread of the examples matters more than the cleverness of the method.
- How you learn it. By doing: sorting.
- Length. 5 short steps. Progress saves on this phone.
Part of Inside AI Models
What a model actually learns from data, where it is strong, and where it fails.