Unsupervised learning asks the model to find structure in data without any labels. Clustering, dimensionality reduction, and density estimation are the prototypical tasks. It sits opposite Supervised Learning, though the line has blurred with the rise of Self-Supervised Learning, which uses unlabeled data to generate its own training signal. Most modern Foundation Model training pipelines in fact lean heavily on this semi-unsupervised approach.
MEVZU N°124ISTANBULYEAR I — VOL. III
Glossary · Beginner · 1990
Unsupervised Learning
A machine learning paradigm in which the model finds patterns in data without any labels.
- EN — English term
- Unsupervised Learning
- TR — Turkish term
- Denetimsiz Öğrenme