AI glossary · Machine learning
Supervised learning
Supervised learning trains an AI model on examples that come with the right answer, such as photos labelled “cat” or “dog”, so it can label new examples.
In more detail
The labels act like a teacher marking homework. The model guesses, compares its guess with the label, and adjusts. It is the most common type of machine learning.
The two main supervised tasks are classification (choosing a category) and regression (predicting a number). The catch is that labelling lots of data takes time and money.
Example
Training a model on past loan applications marked “repaid” or “defaulted” to assess new applications.
Related terms
Unsupervised learningUnsupervised learning finds patterns and groups in data that has no labels, such as discovering types of customers from their shopping habits.ClassificationClassification is a machine learning task where the model sorts things into categories, such as “spam” or “not spam”, or which animal is in a photo.RegressionRegression is a machine learning task where the model predicts a number, such as a house price, tomorrow’s temperature or next month’s sales.Training dataTraining data is the set of examples, such as text, images or past records, that an AI model learns from. Its quality and range shape what the model can do.
Browse related tools
AI tools listed on BroUseAI in these categories.