When an Eyeball Dev Set Becomes Less Useful
Question: Explain why an Eyeball dev set is less useful when the system is trained on a task that people cannot do reliably themselves, and state what a practitioner should do with that Eyeball dev set in that situation.
Sample answer: If humans cannot perform the task well, then manually inspecting examples in an Eyeball dev set is less helpful because people usually cannot tell why the model made a mistake. In that case, the practitioner may decide not to maintain an Eyeball dev set at all.
Key points:
- Humans cannot reliably diagnose the model’s failures on the task.
- Manual inspection becomes less informative.
- The Eyeball dev set can be omitted.
Rubric: The response must explain why the Eyeball dev set is less useful in this setting and state the recommended action of omitting it.
0
1
Tags
Machine Learning
Deep Learning
Machine Learning Strategy
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Yearning @ DeepLearning.AI
Related
Why is a manual review set less useful when people cannot do the task reliably themselves?
An eyeball-style dev set is equally helpful even when humans cannot perform the task well.
When people are poor at a task, it is harder to explain why the model _____ a case the right way.
Match each situation to the correct guidance about whether an eyeball dev set is worthwhile.
Arrange the steps for deciding whether an Eyeball dev set is useful.
A company is training a system to detect tiny defects in industrial microscope images, but even expert inspectors cannot reliably tell when the system is wrong. What should they do about the Eyeball dev set?
A manually reviewed dev set may be omitted when people cannot reliably judge whether the model is correct.
If people cannot judge the task reliably, you might _____ an Eyeball dev set altogether.
Match the manual review concept to its role in model debugging.
Order the reasoning steps that explain why a manual review set adds little value when people cannot reliably do the task themselves.
When an Eyeball Dev Set Becomes Less Useful
Deciding whether to build a manual review set for satellite burst detection.
Why is manual review of mistakes less useful on tasks people cannot do reliably?