« Back to Glossary Index

Classification is a supervised machine learning task where the goal is to classify the elements of a dataset into one element of a finite predetermined list of possible categories or groups, called class. A classical examples is the Iris flower data set: given the length and the width of the both sepals and petals of several Iris flowers, one has to classify each Iris flower, i.e. to detect the correct specie among Iris setosa, Iris virginica, Iris versicolor, etc.

From a technical point of view there is a difference whether there are exactly two classes, and in this case we call the task binary classification, or there are more than two classes, and in this case we call the task multi-class classification – see here and here for technical details.