Essay

Diagnose the 10%/11%/20% error scenario

Question: An algorithm exhibits a 10% training error, an 11% training-dev error, and a 20% dev error. Assuming human-level error is near 0%, analyze the algorithm's performance issues based on these three error metrics. Explain which specific ML problems the algorithm suffers from and which it does not.

Sample answer: The algorithm suffers from high avoidable bias and data mismatch, but it does not suffer from high variance on the training set distribution. The high training error (10%) indicates high avoidable bias. The small 1% gap between the training error and the training-dev error (11%) shows that the algorithm does not suffer from high variance on the training distribution. Finally, the large 9% gap between the training-dev error and the dev error (20%) demonstrates data mismatch.

Key points:

  • Identifies high avoidable bias due to 10% training error.
  • Identifies lack of high variance due to small gap between training and training-dev error (10% vs 11%).
  • Identifies data mismatch due to large gap between training-dev error and dev error (11% vs 20%).

Rubric: The response must identify high avoidable bias, data mismatch, and the lack of high variance. It should justify each using the specific gaps between the provided error metrics.

0

1

Updated 2026-06-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI