What is machine learning?
Quick answer
Machine learning is the part of AI where a model improves at a task by being shown labelled examples, rather than by being programmed with explicit rules.
Middle-school students train an image classifier on photos they take themselves, then deliberately break it to see how data quality changes results.
In context
A model is trained on a dataset, tested on data it has never seen, and judged on how often it gets the unseen cases right. That train-and-test loop is the single most transferable idea in the whole field.
It is also the point where students meet bias in a concrete way. A model trained on a narrow dataset performs badly for everyone outside it, and that is a lesson better learned by building than by lecture.
In a NASCA classroom
Middle-school students train an image classifier on photos they take themselves, then deliberately break it to see how data quality changes results.
Related terms
Artificial intelligence
Artificial intelligence is software that learns patterns from data and uses them to make predictions or generate new content, instead of following rules a person wrote by hand.
Training data
Training data is the collection of examples a model learns from. Its size, balance and quality set the ceiling on how well the finished model can perform.
Model bias
Model bias is a systematic error that makes an AI system perform worse for some groups than others, usually because the training data under-represented them.