All terms
Foundations
Hyperparameter
A configuration value set before training, such as learning rate or batch size.
Definition
A hyperparameter is a configuration value set before training begins, such as the learning rate, batch size, number of layers, or dropout rate. Unlike weights, hyperparameters are not learned from data; they control the optimization process and model architecture. Tuning them well, through grid search, random search, or Bayesian optimization, is often key to good results.