Short Answer

Sign That the Development Set Has Been Overused

Question: After you finish training and selecting your final model, what comparison suggests that you have effectively overfitted the development set?

Sample answer: A warning sign is when the model performs much better on the development set than on the test set, which suggests the development data influenced the model-selection process too strongly.

Key points:

  • Compare development-set performance with test-set performance.
  • A large gap, with development performance much better, indicates overfitting to the development set.

Rubric: The answer must state that development-set performance should be compared with test-set performance and that a much better development-set result is the sign of overfitting.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Machine Learning Strategy

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Yearning @ DeepLearning.AI