Hyperparameter Tuning
The process of optimising configuration parameters that control the learning process of a machine learning model; these parameters are set before training begins and significantly influence model performance.
In plain language
Adjusting the dials that control how an AI learns, such as how fast it learns, how large the model is or how many training cycles to run. It's like adjusting temperature and baking time to get the best cake.
Why this matters
Hyperparameter choices directly affect model performance and fairness. Governance frameworks should require documentation of hyperparameter selections and rationale, particularly for high-risk models, to enable reproducibility and regulatory audit.
Relevance
ImplementationHyperparameter tuning choices affect model quality and fairness and should be documented as part of AI development governance.
Related terms
Putting hyperparameter tuning into practice in your organisation?
Ready to transform your AI strategy?
Partner with Australia's AI strategy and governance specialists. From adoption roadmaps to ISO 42001 audit readiness.