hyperparameter
/ˌhaɪpərˈpærəmiːtər/
A parameter set before training begins, not learned from data
hyperparameter in a sentence
“Tuning hyperparameters like learning rate improved model performance.”
Origin of hyperparameter
From Greek hyper (over, beyond) + para (beside) + metron (measure)
Related Words
epoch
One complete pass through the entire training dataset
batch size
The number of samples processed before updating the model
loss function
A measure of how wrong the model's predictions are
bias
Prejudice in favor of or against one thing, person, or group
algorithm
A process or set of rules to be followed in calculations
neural network
A computing system inspired by biological neural networks