Model Training & Adaptation
Discriminative model
AI that learns to predict a label or answer from information it is given.
Example
An AI system separates spam from legitimate messages.
Why people use it
It helps AI choose a category or estimate a target from available clues.
What you'll hear
“Which group does this case belong to?”
What this means for you
Match the AI system type to the task you need performed.
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 a discriminative AI system designed primarily to generate new examples?
- No. Its central purpose is predicting distinctions or targets, unlike a generative AI system.
- Can it produce a confidence score?
- Some methods do, but the meaning and reliability of that score need checking.
- Does it need good examples of every situation?
- Gaps in teaching examples can make unfamiliar cases harder to handle well.