Case Study

Decide how a team should use a dev set that is too small to divide.

Case context: A team wants separate development subsets, but its dev set is not big enough to split. The team still needs to examine errors manually, select a model, and tune hyperparameters.

Question: What should the team designate as its Eyeball dev set, and which activities should it perform with that set?

Sample answer: The team should designate the entire dev set as the Eyeball dev set. It should use that set for manual error analysis, model selection, and hyperparameter tuning.

Key points:

  • Do not divide a dev set that is not big enough to split.
  • Use the entire dev set as the Eyeball dev set.
  • Perform manual error analysis with it.
  • Use it for model selection and hyperparameter tuning.

Rubric: Full credit requires choosing the entire dev set, naming its Eyeball dev set role, and listing all three supported activities. Partial credit applies when the decision is correct but the activities are incomplete.

0

1

Updated 2026-07-20

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI