Skip to content
Learn Motion
ExploreHow it worksMembership
Log in
Learn Motion

How Machines Learn from Data

1Learning Without Being Told the Rules2Measuring Mistakes and Adjusting3Generalizing Beyond the Training Data4The Main Ways Machines Learn
Learning Without Being Told the Rules

What Counts as an Example

2 / 3
Look closely at the spam example on this page. The email is the input, and the word spam is the correct output, and the two together are what we call one training example. The pairing is the whole point. If you handed the model a pile of emails with no labels, it would have no way to know which ones were supposed to be spam. It is the correct answer attached to each input that gives the model something to compare against. That is also why a mislabeled email is worse than a missing one: it actively teaches the wrong lesson.
0:00 / 0:00

A training example is one input paired with its correct output. A dataset is a collection of such pairs, and its size is the number of examples it contains.

One example in the spam filter

Consider a single email whose subject is "Claim your prize now" and whose body contains a suspicious link. If a person has already reviewed it and marked it as spam, then this email and the label "spam" together form one training example. The email text is the input; the word "spam" is the correct output. Ten thousand such emails, each with its own label, form the dataset the model learns from.

The correct output is often called a label. A mislabeled example teaches the model something false, so the accuracy of the labels is part of the data's quality.

Previous2 / 3Next

Learn Motion

Generate a course. Learn it properly.

Operated by Wuhan Daoyin Technology Co., Ltd.

Contact: [email protected]
Privacy PolicyTerms of Service

© 2026 Learn Motion