Hyperparameter

What is Hyperparameter?

A configuration variable that is external to the model and whose value cannot be estimated from data (e.g., Learning Rate, Batch Size, Number of Layers). These must be tuned by the engineer.

Where did the term "Hyperparameter" come from?

The 'art' of machine learning.

How is "Hyperparameter" used today?

What ML engineers spend 80% of their time tuning.

Related Terms