Explain how the size of a meaningful accuracy improvement should influence dev set size.
Question: In a concise analytical response, explain why teams targeting smaller accuracy improvements may require larger dev sets. Use the 0.1% and 0.01% examples from the source.
Sample answer: Dev set size should reflect the smallest accuracy change the team considers meaningful. A 100-example dev set cannot detect a difference such as 90.0% versus 90.1%, while 10,000 examples gives a good chance of detecting a 0.1% improvement. Mature and important applications may value improvements as small as 0.01%, so their dev sets could be much larger than 10,000. However, a dev set need not be much larger than what is required to detect the meaningful change.
Key points:
- Dev set size depends on the meaningful accuracy change.
- One hundred examples cannot detect 90.0% versus 90.1%.
- Ten thousand examples gives a good chance of detecting a 0.1% improvement.
- Detecting a 0.01% improvement may require much more than 10,000 examples.
- The dev set need not be much larger than necessary.
Rubric: A strong response connects smaller target improvements to larger dev sets, accurately uses the 100-example, 10,000-example, 0.1%, and 0.01% evidence, and notes that unnecessary additional size is not required.
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)
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Small Dev Sets Cannot Detect Tiny Accuracy Differences
Common Dev Set Sizes for Detecting 0.1% Improvements
High-Value Applications May Need Larger Dev Sets
Statistical Significance Tests on Dev Set Changes
Which dev set best supports detecting a 0.1 percentage-point accuracy improvement?
A dev set should always be made as large as possible, even beyond what meaningful-change detection requires.
A dev set of _____ examples gives a good chance of detecting a 0.1% improvement.
Match each accuracy-detection goal with its dev set implication.
Order the reasoning process for sizing a dev set around a meaningful accuracy change.
Explain how the size of a meaningful accuracy improvement should influence dev set size.
Decide whether a mature recommendation system needs a larger dev set.
Why is a 100-example dev set inadequate for comparing 90.0% and 90.1% accuracy?
When is a dev set much larger than 10,000 examples most justified?
A team satisfied with detecting meaningful changes need not enlarge its dev set far beyond that requirement.