Los datos holdout son datos excluidos intencionalmente del entrenamiento para poder usarlos en la evaluación del rendimiento del modelo. Los conjuntos de validación y prueba son formas comunes de datos holdout. Ayudan a estimar qué tan bien generaliza un modelo más allá de los ejemplos de los que aprendió.
Examples intentionally not used ("held out") during training. The validation dataset and test dataset are examples of holdout data. Holdout data helps evaluate your model's ability to generalize to data other than the data it was trained on. The loss on the holdout set provides a better estimate of the loss on an unseen dataset than does the loss on the training set.
A side-by-side comparison of Test Set and Holdout Data. Understand how a reserved test set relates to the broader category of data excluded from training for validation or evaluation.
A side-by-side comparison of Cross-validation and Holdout Data. Understand how repeated split-based evaluation differs from reserving data outside training for evaluation.