Glossary term
Glossary term
Training and Fine-Tuning
Unsupervised learning is when AI is trained on data without labels. It learns by spotting patterns, clusters, or relationships on its own, which is useful for organizing data or discovering hidden insights without manual setup.
K-means and DBSCAN clustering in scikit-learn are classic unsupervised learning algorithms.
Word2Vec and GloVe word embeddings were trained using unsupervised learning on large text corpora.
The pre-training stage of all modern LLMs uses self-supervised learning, a form of unsupervised learning.