An AI machine learning method that trains a neural network by feeding it predefined sets of inputs. Supervised learning causes the network to learn by example. The network is fed pre-labeled inputs or input-output pairs so that it can recognize which input patterns produce which outputs.
Unsupervised and Semi-Supervised
Contrast with "unsupervised learning," whereby there are no labels attached to the input. The AI network detects patterns in the unlabeled input, which may otherwise be hidden and never known. Unsupervised learning is less common than supervised learning; however, an in-between approach uses both methods.
Semi-supervised learning employs both labeled and unlabeled sets of data. It is especially useful with huge amounts of data. Labeling only a small amount of input saves a lot of human time, but it can provide enough samples to let the system identify the larger unlabeled set. See
machine learning and
deep learning.