Learn Before
Other factors in choosing which error type to fix first
Question: When you use error analysis to decide what to improve next, what two factors should you weigh in addition to how often each error type occurs?
Sample answer: You should consider the likely improvement from fixing each error type and the amount of effort required to address it.
Key points:
- Expected improvement from fixing each error type.
- Effort or work needed to make the fix.
Rubric: The answer must identify both non-frequency factors used to prioritize improvement work.
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 does error analysis not directly give you when deciding the next improvement to make?
Error analysis alone can identify the single highest-priority improvement with no further judgment.
Error analysis does not provide a fixed priority rule
Match each review metric to its role in deciding what to fix first.
Prioritize work using error analysis.
Which two factors should be considered in addition to error percentages when choosing what to fix first?
When deciding which error categories to address first, the effort required for each fix should be considered.
Tradeoffs in Choosing Which Problems to Fix First
Match each description to the role it plays in deciding which error to fix first.
Order the steps for deciding whether one error category should be prioritized first.
Why Error Percentages Alone Do Not Determine Task Priority
Choosing between two fixes after review of failure patterns.
Other factors in choosing which error type to fix first