Self-Supervised Learning (самообучение с самосупервизией)

Also known as: Self supervised Learning

Caesar AI Atlas Definition

Self-supervised learning — подход machine learning, создающий training signals из самих unlabeled data. Он преобразует аспекты unsupervised problem в supervised learning путем generating surrogate labels, что полезно, когда labeled data scarce, но unlabeled data abundant.

Other Definitions

Self-Supervised Learning (самообучение с самосупервизией) Source

A family of techniques for converting an unsupervised machine learning problem into a supervised machine learning problem by creating surrogate labels from unlabeled examples. Some Transformer-based models such as BERT use self-supervised learning. Self-supervised training is a semi-supervised learning approach.

Also Referenced In

expert.ai — Glossary of AI Terms

Concept Comparisons

Technical AlternativeMachine Learning

Self-supervised Learning vs Semi-Supervised Learning

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.