In machine learning, hyperparameter is a parameter, such as the learning rate or choice of optimiser, which control the learning process. In contrast to normal (i.e. not hyper) parameters which are determined by the model itself during the learning phase, hyperparameters cannot be inferred while fitting the model to the training set.
« Back to Glossary Index
©2026 Radicalbit is owned and operated by Fortitude Group Srl
All rights reserved VAT IT04268680263