Skip to content

Model Training & Adaptation

DBSCAN

Density-based spatial clustering of applications with noise

A method that groups closely packed examples together and can leave isolated examples outside the groups.

Example

An AI system finds dense geographic clusters while leaving scattered observations ungrouped.

Why people use it

It finds dense groups without forcing isolated cases into a group.

What you'll hear

“Let isolated points remain outside the clusters.”

What this means for you

Check sensitivity to distance, density settings and feature scaling.

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 two nearby groups be accidentally joined?
Yes. A chain of closely spaced examples can connect areas people might prefer to treat as separate.
Must we specify the number of groups first?
No. The groups emerge from the chosen density and distance settings.
Can very different group densities be difficult?
Yes. One set of settings may not suit both tightly packed and widely spread groups.

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