Identifying the specific type of bias in the 10%/11%/12% error scenario
Question: If your algorithm has a 10% error on the training set, an 11% error on the training-dev set, and a 12% error on the dev set, what specific type of bias is considered high?
Sample answer: The algorithm has high avoidable bias.
Key points:
- High avoidable bias.
- Relates to poor performance on the training set.
Rubric: Award full credit for identifying 'avoidable bias' (or 'high avoidable bias').
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 10% training, 11% training-dev, and 12% dev error primarily indicate about a model?
An algorithm with 10% training error, 11% training-dev error, and 12% dev error is doing poorly on the training set.
An algorithm with 10% training, 11% training-dev, and 12% dev error has high _____ bias on the training set.
Match each error metric in ML Yearning's high avoidable bias scenario to its correct value or diagnosis.
Order the diagnostic steps for identifying high avoidable bias in ML Yearning's 10%/11%/12% error scenario.
In the 10%/11%/12% scenario, what does the 1% gap between training and training-dev errors tell us?
High variance (overfitting) is the primary error problem when training error is 10%, training-dev error is 11%, and dev error is 12%.
With 10% training, 11% training-dev, and 12% dev error, the algorithm is doing poorly on the _____ set.
Match each error problem type to the signal that most directly reveals it in the ML Yearning framework.
Order the reasoning steps for concluding that avoidable bias is the main problem when all three errors are clustered high.
Analyzing the root cause when training error is 10% and dev error is 12%
Diagnosing primary errors given 10% training, 11% training-dev, and 12% dev rates
Identifying the specific type of bias in the 10%/11%/12% error scenario