Glossary term
Glossary term
Training and Fine-Tuning
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.
Created for this library
A document classification team uses semi-supervised learning to combine a small labeled set with a large unlabeled corpus.
A medical AI team uses semi-supervised learning on unlabeled scans alongside a small labeled set to improve a rare-disease classifier.
An NLP team uses semi-supervised learning to expand training data by combining a small labeled set with a large unlabeled web corpus.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License