Explain why an undivided small dev set can serve as the Eyeball dev set.
Question: In a concise analytical response, explain the recommended treatment of a dev set that is not big enough to split and identify its permitted uses.
Sample answer: When the dev set is not big enough to split, the recommendation is to keep it intact and use the entire set as the Eyeball dev set. It can then support manual error analysis, model selection, and hyperparameter tuning.
Key points:
- The dev set is not big enough to split.
- The entire dev set becomes the Eyeball dev set.
- It is used for manual error analysis.
- It is used for model selection.
- It is used for hyperparameter tuning.
Rubric: A strong response states the small-set condition, recommends using the entire dev set as the Eyeball dev set, and identifies all three named uses. Partial credit should be given for a correct recommendation with one or two uses.
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.