1.2Standard
Training accuracy is high but validation accuracy is low.
Improve generalization.
Choose two responses.
× Incorrect
Monitor validation performance and consider regularization, early stopping, independent evaluation, and data augmentation.
Detailed explanation
IncorrectMore training always improves unseen performance
Training can overfit.
CorrectMonitor validation performance and consider early stopping or regularization
Model complexity can be controlled.
CorrectUse independent data and adjust capacity or augmentation as needed
Generalization is tested.
IncorrectDeploy the highest training-accuracy model directly
Validation is ignored.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.2の過学習、正則化、早期終了、一般化性能を確認する。
Official references
What to confirm
訓練性能と未知データ性能の差を見て過学習対策を選べる。
Key points
- Overfitting
- Regularization
- Generalization
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Overfitting
Learning noise or specific examples so performance falls on unseen data.
Regularization
A constraint or penalty that discourages unnecessarily complex models.
Question IDAWS-AIF-416
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue