Skip to content

AI Foundations

Convolutional neural network

A type of AI that learns to find small patterns, especially shapes and details within pictures.

Example

An AI system learns visual features useful for recognizing products.

Why people use it

It helps AI find useful visual patterns such as edges, shapes and textures.

What you'll hear

“This system learned which shapes help identify the product.”

What this means for you

Test performance on the actual image conditions where the AI system will be used.

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 moving an object within a picture affect recognition?
It can, though reusing pattern checks helps the system recognize similar shapes in different positions.
Does it need someone to describe every useful shape?
No. It can learn useful visual patterns from examples during training.
Can it focus on the wrong detail?
Yes. A background or label in the pictures may influence it more than the object itself.

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