Supervised learning: Difference between revisions
No edit summary |
|||
| Line 3: | Line 3: | ||
A machine-learning approach in which an AI system is trained on a dataset that has been labeled by people, usually when there is a specific, known output in mind. | A machine-learning approach in which an AI system is trained on a dataset that has been labeled by people, usually when there is a specific, known output in mind. | ||
# | # For example, a model may be trained on millions of pictures explicitly labeled as either ''zebra'' or ''horse''. The AI learns the characteristics of each animal so it can sort new images into those predefined categories. | ||
====Related terms==== | ====Related terms==== | ||
Latest revision as of 19:14, 9 May 2026
English
[edit | edit source]A machine-learning approach in which an AI system is trained on a dataset that has been labeled by people, usually when there is a specific, known output in mind.
- For example, a model may be trained on millions of pictures explicitly labeled as either zebra or horse. The AI learns the characteristics of each animal so it can sort new images into those predefined categories.