Skip to content

What is Label?

In machine learning, a label is the known correct output or category assigned to a training data example that a model learns to predict.

Labels are the target values used in supervised learning. They tell the algorithm what the desired answer should be for each input during training.

Without labels, models cannot learn the mapping from features to outcomes. The quality and accuracy of labels directly affect how well the model performs on new data.

Labels can be categories (e.g., 'cat' or 'dog') for classification or numeric values for regression tasks.

Example

In a dataset of photos, each image might have a label such as 'cat' or 'dog' so the model can learn to recognize animals correctly.

Why it matters

Labels are essential for training supervised models that power most practical AI applications today, from image recognition to spam detection.

Frequently asked questions

Features are the input variables describing the data, while labels are the output the model tries to predict.