Skip to content

AI Foundations

Sigmoid function

An S-shaped calculation often used to turn scores into numbers between zero and one.

Example

A prediction tool turns a raw score into a number between zero and one.

Why people use it

It turns a wide range of scores into values between zero and one.

What you'll hear

“Map this score onto a bounded scale.”

What this means for you

Compare the stated chances with what actually happens.

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 it turn a very large score into exactly the same-sized chance?
No. Its result approaches an upper limit rather than growing without bound.
Can very large scores produce only tiny changes afterward?
Yes. Near either end of the curve, further score changes have a smaller effect.
Is it used only for final predictions?
No. Related bounded calculations can also be used inside a network.

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