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
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
What should you do when the dev set is too small to divide into separate subsets?
A dev set that is too small to split can still support all three named development activities.
If the dev set cannot be split, use the _____ dev set as the Eyeball dev set.
Match each source element to its role in the small-dev-set recommendation.
Order the reasoning for handling a dev set that may be too small to split.
Explain why an undivided small dev set can serve as the Eyeball dev set.
Decide how a team should use a dev set that is too small to divide.
Name the three uses of the entire dev set under the small-set recommendation.
Which development plan best follows the recommendation for an unsplittable dev set?
Using the full small dev set as an Eyeball dev set excludes hyperparameter tuning.