Skip to content

Model Training & Adaptation

Supervised learning

Machine learning that learns from examples paired with known answers.

Example

An AI system learns to distinguish spam from messages labeled legitimate.

Why people use it

It teaches AI from examples where the desired answer is already known.

What you'll hear

“We showed it examples marked right or wrong.”

What this means for you

Ask how performance was checked on unseen, relevant examples.

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

Can accurate training answers guarantee good future predictions?
No. New cases may differ from the examples used for learning.
What happens if the teaching examples are wrong?
The AI may learn those mistakes and repeat them when it encounters new cases.
Does it need a person watching every lesson?
No. People prepare or check the examples, but computers usually carry out the learning process automatically.

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