Also known as: Semi-Supervised Machine Learning · Semi Supervised Learning
L’apprentissage semi-supervisé est une approche d’apprentissage automatique qui utilise à la fois des données étiquetées et non étiquetées pendant l’entraînement. Il est utile lorsque les exemples étiquetés sont coûteux ou limités, mais que de grands volumes de données non étiquetées peuvent aider à améliorer la représentation, la classification ou la prédiction.
(Also weak supervision.) A machine learning training paradigm characterized by using a combination of a small amount of human-labeled data (used exclusively in supervised learning), followed by a large amount of unlabeled data (used exclusively in unsupervised learning).
Training a model on data where some of the training examples have labels but others don't. One technique for semi-supervised learning is to infer labels for the unlabeled examples, and then to train on the inferred labels to create a new model. Semi-supervised learning can be useful if labels are expensive to obtain but unlabeled examples are plentiful. Self-training is one technique for semi-supervised learning.
A way of training machine learning systems for a specific application. An AI system uses a mix of supervised and unsupervised learning and labelled and unlabelled data. This type of learning is useful when it is difficult to extract relevant features from data and when there are high volumes of complex data, such as identifying abnormalities in medical images, like potential tumours or other markers of diseases. See also supervised learning, unsupervised learning, reinforcement learning and training datasets.
A side-by-side comparison of Supervised Learning and Semi-Supervised Learning. Understand how learning from labeled examples differs from combining labeled and unlabeled data.
A side-by-side comparison of Self-supervised Learning and Semi-Supervised Learning. Understand how each uses unlabeled data and why the role of labels differs.