Hyperparameter
Configuration settings set before training that control the learning process, not learned from data.
In-depth explanation
Hyperparameters are external configurations that affect how a model learns. Unlike model parameters (learned during training), hyperparameters are set by the practitioner. Examples include learning rate, number of layers, regularization strength, and batch size. Hyperparameter tuning—finding optimal values—significantly impacts model performance.
Examples
Related terms
More in Machine Learning
Classification
Predicting which category or class an input belongs to from a set of predefined categories.
Cross-Validation
A technique to evaluate model performance by training and testing on different subsets of data.
Ensemble Learning
Combining multiple models to produce better predictions than any single model.
Feature
An individual measurable property or characteristic of data used as input to a machine learning model.
Feature Engineering
The process of using domain knowledge to create new features that improve model performance.
Gradient Descent
An optimization algorithm that iteratively adjusts model parameters to minimize the loss function.
Master Hyperparameter.
Learn how to apply this concept with hands-on projects in our comprehensive AI programs.