Core Concepts
Hyperparameter
Hyperparameters are configuration variables set before training—such as learning rate, batch size, number of layers, and dropout rate—as opposed to model parameters which are learned from data. Choosing good hyperparameters is critical to model performance.
Hyperparameter tuning (using grid search, random search, or Bayesian optimization) is one of the most time-consuming parts of ML development. AutoML tools aim to automate this process.
Authority Links
Related Terms
Techniques & Methods
Training
Teaching a model to make accurate predictions by exposing it to large datasets.
Core Concepts
Overfitting
Model learns detail and noise in training data too thoroughly, reducing generalization.
Techniques & Methods
Regularization
Techniques that prevent overfitting by penalizing model complexity during training.
Model Components
Parameter
A learnable variable within a model whose value is adjusted during training to minimize prediction error.