An AI machine learning method that trains a neural network by example. Supervised learning feeds the network predefined and labeled inputs in both the training and fine tuning stages of the model. Supervised learning was common in early machine learning; however, today's large models may employ any of the following methods as well. See
AI training and
AI data labeling.
Semi-Supervised = Labeled and Unlabeled
Employs labeled and unlabeled datasets. Labeling a small amount of data can provide enough samples to let the model identify the larger unlabeled set.
Unsupervised = No Labels
No labels at all in unsupervised learning. The AI neural network detects patterns by recognizing common attributes. Unsupervised learning is less widely used than supervised learning, but both methods are used to train similar models.
Self-Supervised = Generated Labels
Used heavily in today's large models, self-supervised learning creates its own labels. See
AI model,
machine learning and
deep learning.