Word
hyperparameter
Definition
n. A setting you choose before training an AI, instead of something the AI learns on its own.
n. A configuration value set prior to training, as distinct from parameters learned directly from the training data.
Examples
“The researchers adjusted the learning-rate hyperparameter.”
“Choosing the right hyperparameters can improve model performance.”
Examples
simple
“The researchers adjusted the learning-rate hyperparameter.”
contextual
“Choosing the right hyperparameters can improve model performance.”
Real-World Examples
“The rate of perplexity decrease over training steps indicates whether the model is still learning or has plateaued, helping practitioners decide when to stop training or adjust hyperparameters.” Etymology
hyper- from Greek "over, beyond" + parameter.
Original etymology written by Shinotoshi Nakamura.
Domain
Technology
Scan code
englishreference.com/q/hyperparameter