Model Training & Adaptation
Hyperparameter tuning
Comparing different setup choices to find ones that help an AI perform well.
Example
A team compares learning rates on a independent checking set.
Why people use it
It finds useful learning settings through comparison rather than guesswork.
What you'll hear
“Which settings worked best on the practice checks?”
What this means for you
Avoid choosing settings from repeated inspection of the final test set.
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 the best settings change later?
- Yes. New information, different tasks or changed computing limits can make other settings more suitable.
- Can settings that win on one collection lose on another?
- Yes. The best choice can depend on the task and the examples used.
- Why keep a final test separate?
- Repeatedly choosing settings from the same test can make the final score look better than real performance.