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.
Related terms
Supervised learning is a machine learning method where a model is trained on data that already has correct answers attached, so it can learn to predict those answers for new data.
In AI and machine learning, a feature is an individual measurable piece of data that serves as an input variable for a model.
Training data is the dataset of examples that a machine learning model learns from during the training process. It contains input features paired with known outputs so the model can discover patterns.
Classification is a supervised machine learning task that assigns input data to one of several predefined categories or classes based on patterns learned from labeled training examples.
Batch size is the number of training examples processed together in a single forward and backward pass during model training.
Data augmentation is a technique that artificially increases the size and diversity of a training dataset by creating modified versions of existing data samples.