How should a team handle about 1,000 errors in a 5,000-example dev set?
Case context: A team has a dev set of 5,000 examples with a 20% error rate, producing about 1,000 misclassified examples. Examining every error manually would take a long time.
Question: What dev-set arrangement should the team choose, and how should it use each portion?
Sample answer: The team should explicitly split the dev set into a portion it manually examines and a portion it does not examine. It should conduct error analysis on the examined portion and use the hands-off portion to tune parameters. Because the examined portion will be overfit more rapidly, comparing the portions can help the team detect overfitting caused by its manual error analysis.
Key points:
- Explicitly split the large dev set into two portions.
- Manually inspect only the examined portion.
- Keep the other portion free from manual inspection.
- Use the unexamined portion for parameter tuning.
- Use the separation to detect overfitting of the examined portion.
Rubric: The response should recommend an explicit two-part split, assign manual error analysis to the examined portion, assign parameter tuning to the unexamined portion, and state how the split helps detect overfitting.
0
1
References
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Machine Learning Yearning (Deeplearning.ai)
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Eyeball Dev Set
Blackbox Dev Set
Using the Entire Dev Set as the Eyeball Dev Set When It Is Too Small to Split
Why explicitly divide a large dev set into examined and unexamined portions?
Does manual examination make one dev subset more prone to overfitting?
The unexamined dev subset can be used to tune _____.
Match each dev-set concept with its role or consequence.
Order the reasoning for handling a large dev set with many errors.
Explain how an explicit dev-set split exposes overfitting from manual error analysis.
How should a team handle about 1,000 errors in a 5,000-example dev set?
What distinct purpose does each portion of the split dev set serve?
Which development pattern signals overfitting to the manually inspected subset?
Should a dev set that is too small to divide still be split into two portions?