Supervised Learning is a machine learning approach where models are trained on labeled data—input examples paired with correct output answers. The algorithm learns to map inputs to outputs by studying these examples, adjusting its parameters to minimize errors between its predictions and the known correct answers. This method is widely used for tasks like image classification, spam detection, and speech recognition, where large datasets of labeled examples are available to teach the model.
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News
Explore Similar Terms:
Unsupervised Learning | Reinforcement Learning | Training Data

At an HAI workshop, researchers examined AI approaches that could help us save a struggling planet.
At an HAI workshop, researchers examined AI approaches that could help us save a struggling planet.


With Trove, weakly supervised NLP of clinical text is fast, adaptive, shareable, and high performing.
With Trove, weakly supervised NLP of clinical text is fast, adaptive, shareable, and high performing.


Stanford scholars explore advances in foundation models, explore the next-generation chip, and study causal models at the recent Hoffman-Yee Symposium.
Stanford scholars explore advances in foundation models, explore the next-generation chip, and study causal models at the recent Hoffman-Yee Symposium.
