Hyperparameter
/ˈhaɪpərˌpærəmɪtər/
Definition
A configuration value set before training (learning rate, batch size, layer count) that controls the training process.
Example in context
"We tuned the learning rate hyperparameter from 0.01 to 0.001 — validation loss improved consistently."
Practice this term
Master Hyperparameter in context by working through exercises in the Data Science & ML module. You'll see the term used in real engineering scenarios with multiple-choice, fill-in-the-blank, and matching drills.