Model Training & Adaptation
Federated learning
Teaching AI across separate devices or organizations while sharing learning changes instead of routinely pooling their original records.
Example
Several sites contribute AI system updates from their local collections of information.
Why people use it
It lets several locations contribute to learning without routinely pooling all their original records.
What you'll hear
“Keep the records local and share learning updates.”
What this means for you
Assess the full privacy and security design, not just where raw data stays.
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
- Does federated learning guarantee privacy by itself?
- No. Updates can still expose information without appropriate safeguards.
- Can different locations have very different examples?
- Yes. Differences between sites can make the combined learning harder.
- Does each device have to stay connected continuously?
- Not necessarily. The design can organize when participants receive and send updates.