Model Training & Adaptation
Self-supervised learning
AI learning from practice tasks made from the material itself, rather than answers separately supplied by people.
Example
An AI system learns to predict hidden words in a passage.
Why people use it
It allows learning from large collections without people labeling every example by hand.
What you'll hear
“The system makes its own practice questions from the text.”
What this means for you
Distinguish automatic target creation from the absence of oversight.
Can you control it?
Developer-only
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Is predicting missing words the only practice task?
- No. Other approaches learn from relationships between pictures, sounds or different parts of the available material.
- Does that mean it learns without any human choices?
- No. People still choose the material, learning task and way the system is built.
- Can it learn harmful patterns too?
- Yes. Learning automatically from material does not remove problems already present in that material.