AI Dictionary
Hyperparameter
Definition
A configuration that is external to the model and whose value cannot be estimated from data.
Deep Dive
A hyperparameter is a configuration variable that is external to a machine learning model and whose value cannot be estimated from the data itself. Unlike model parameters, which are learned during the training process (e.g., weights and biases in a neural network), hyperparameters are set by the data scientist *before* training begins and dictate how the model learns or its overall architecture.
Examples & Use Cases
- 1The learning rate in a neural network, which controls the step size during optimization
- 2The number of clusters (k) to form in a K-Means clustering algorithm
- 3The maximum depth of a decision tree in a classification model
Related Terms
Model ParameterMachine LearningModel Tuning