Machine learning (ML)
Building a program by training it on examples. The training shapes how it handles new input.
A person writes the rules: “If the email mentions ‘lottery’, mark it as spam.”
Show the program ten thousand emails marked spam or not. It works out the patterns itself.
Most of what is called AI today is the second kind. It is powerful because nobody had to write the rules, and hard to explain for exactly the same reason.
The fuller definition
Machine learning is a way to build systems by fitting their behavior to data rather than specifying every decision as a hand-written rule.
Go deeper
- Examples
Labelled documents
- Training
Adjust model parameters
- Prediction
Classify a new document
A simplified relationship, not a screenshot or a complete design.
A concrete example
A classifier learns patterns associated with invoices from labelled examples, then classifies an unseen document.
The distinction that matters
Learning during training differs from reading new material during an ordinary conversation.
Related terms
Training
Adjusting a model with examples and a learning rule. The aim is to improve how it handles tasks.
FoundationsInference
The act of running a trained model to get an answer. In law the word means something else: a conclusion drawn from evidence.
Training & generationDataset
A collection of examples used to train or test a model.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.