Skip to content
ontologydriven
Sign out

Dictionary

Words, grammatical forms and meanings linked to the ontology.

hyperparameter en · NOUN

Etymology

From hyper- + parameter.

Meanings

  1. (qualifier:Bayesian statistics) A parameter of a prior (as distinguished from inferred parameters of the model for the underlying system under analysis).
    • this model has four hyperparameters
    • The exact interpretation of these hyperparameters becomes clearer once you have seen their role in the posterior and, hence, we defer a deeper discussion of prior elicitation until the next section. 2003, Gary Koop, Bayesian Econometrics, John Wiley & Sons Ltd., page 19:
  2. (qualifier:machine learning) A parameter whose value is set before the learning process begins.
    • The ideal learning algorithm just takes a dataset and outputs a function, without requiring hand tuning of hyperparameters. 2016, Ian Goodfellow, Yoshua Bengio, Aaron Courville, chapter 11, in Deep Learning, MIT Press, →ISBN, page 420:
    • “Model behaviour is not determined by architecture, hyperparameters, or optimizer choices,” he said, referring to the technical difficulties of training a language model. “It’s determined by your dataset, nothing else. […]” 2024 May 4, Alex Hern, Dan Milmo, quoting James Betker, “Danger and opportunity for news industry as AI woos it for vital human-written copy”, in The Guardian, →ISSN:

Forms

SpellingFeaturesLabelsSource
hyperparameters Number=Plur lexicographic

Coordinates

parameter · parameter · metaparameter · subparameter · subparameter · metaparameter

Deriveds

hyperparametric

Relateds

hyperprior

Synonyms

superparameter

Translations (8)

de Hyperparameter (Bayesian statistics: parameter of a prior) · ru гиперпараметр (machine learning: parameter whose value is set before the learning process) · ru гиперпараметр (Bayesian statistics: parameter of a prior) · fi hyperparametri (Bayesian statistics: parameter of a prior) · pt hiperparâmetro (Bayesian statistics: parameter of a prior) · bg хиперпараметър (machine learning: parameter whose value is set before the learning process) · bg хиперпараметър (Bayesian statistics: parameter of a prior) · fr hyperparamètre (Bayesian statistics: parameter of a prior)