Model Training & Adaptation
Semi-supervised learning
Teaching AI with a mixture of examples that have answers attached and examples that do not.
Example
AI learns from some labeled pictures alongside many pictures without labels.
Why people use it
It makes use of a large collection when only some examples have checked answers.
What you'll hear
“Only a small part of this collection has been labeled.”
What this means for you
Compare results with learning from the labeled examples alone.
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
- Does unlabeled data always improve the result?
- No. Incorrect assumptions or poor data can reduce performance.
- Can the unlabeled portion describe a different kind of case?
- Yes, and that mismatch can make the additional material less helpful.
- Does the method still need a final independent check?
- Yes. Learning from more material does not establish how well it handles genuinely new cases.