Skip to content

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.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice