Hyperparameter tuning
Practice Flashcards
Flip to reveal answersParameter or hyperparameter — how do you tell?
Track your progress — Sign up free to save your progress and get smart review reminders based on spaced repetition.
All 5 Flashcards — Hyperparameter tuning
Sign up free to track progress and get spaced-repetition review schedules.
Question
Parameter or hyperparameter — how do you tell?
Answer
Ask whether it was **chosen before training started**. If the model worked it out from the data, it is a parameter.
Question
What does the learning rate control?
Answer
How big a step each update takes. **Too high** overshoots the minimum and never settles; **too low** never arrives in the time available.
Question
Why are three data sets used?
Answer
**Training** learns parameters, **validation** chooses hyperparameters, **test** is opened once to report. Tuning on the test set leaks it.
Question
What is cross-validation?
Answer
Splitting into k folds, training on k−1 and testing on the held-out one, rotating — so every record is tested exactly once.
Question
Grid search or random search?
Answer
**Grid** tries every combination and is exponentially expensive. **Random** samples within ranges and usually finds something good sooner, because few hyperparameters matter much.
Read the notes
Full study notes for Hyperparameter tuning
Topic 4.3 hub
Machine learning approaches
More from Topic 4.3
All flashcards in this topic
Computer Science exam skills
Paper structures & tips
Track your progress with spaced repetition
Sign up free — Aimnova tells you exactly which cards to review and when, so you remember everything before your IB exam.
Start Free