Supervised learning is a type of machine learning in which a machine learning model is trained using labelled examples. That is, the model is trained with input data and corresponding correct answers.

In supervised training, the model learns to make predictions or classifications from the input data and corresponding labels. For example, in image classification, the model can be trained with images labelled with corresponding categories (e.g. dogs, cats, cars, etc.) so that it can classify new images into one of those categories.

There are different types of supervised training algorithms, including regression and classification algorithms. Regression algorithms are used to predict continuous numerical values, such as the price of a house or the number of sales in a given month. Classification algorithms are used to predict discrete categories, such as the image classification categories mentioned above.

Supervised training is a widely used learning technique in the field of artificial intelligence and machine learning, as it allows training accurate and useful models for a wide variety of applications. However, a limitation of this type of training is that it requires large labelled datasets, which can be costly and difficult to obtain in some cases.