Multiclass classification is a supervised learning task in which each example is assigned one class from three or more possible classes. It differs from binary classification, which has only two classes, and may use methods such as softmax outputs or one-vs-rest classifiers.
In supervised learning, a classification problem in which the dataset contains more than two classes of labels. For example, the labels in the Iris dataset must be one of the following three classes: - Iris setosa - Iris virginica - Iris versicolor A model trained on the Iris dataset that predicts Iris type on new examples is performing multi-class classification. In contrast, classification problems that distinguish between exactly two classes are binary classification models. For example, an email model that predicts either spam or not spam is a binary classification model. In clustering problems, multi-class classification refers to more than two clusters. See Neural networks: Multi-class classification in Machine Learning Crash Course for more information.
A classification case where the label is one out of three or more classes. For more information, see the Multiclass classification section of the Machine learning tasks topic.
A machine learning model that predicts values that belong to a limited, pre-defined set of permissible values. For example, "Is this product a book, movie, or clothing?"