Self-Supervised Learning
Definition
Self-supervised learning automatically generates learning objectives from the available data.
Learning from target signals automatically generated from the data, without requiring manual labels for each example.
Simply explained
For example, a model hides words in the text and learns to predict them from the remaining text.
Why it matters in practice
The term helps to select, develop, evaluate AI systems in a well-founded manner and realistically assess their technical risks.
Example from business
A model learns text representations by predicting masked words.
Limits and pitfalls
- Do not equate self-supervised learning with unsupervised learning or with no data risks.
Origin & history
Self-Supervised Learning evolved from unsupervised representation learning and became central for language, image, and audio.
Use in mid-sized companies
- Possible application: A model learns text representations by predicting masked words.
Frequently asked questions
What does self-supervised learning mean?
Learning from target signals automatically generated from the data, without requiring manual labels for each example. What mistakes should be avoided? Equating self-supervised learning with unsupervised learning or with no data risks.
Sources
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: