Short Answer

Indicator of High Variance from Error Sets

Question: If a model's optimal error rate is about 0% and its training error is 1%, what specific error rate on the training-dev set in the provided scenario indicates that the model has high variance?

Sample answer: A training-dev error rate of 5% indicates that the model has high variance when compared to the 1% training error.

Key points:

  • 5% training-dev error.
  • The gap between 1% training error and 5% training-dev error indicates the variance.

Rubric: The answer must explicitly identify the 5% error rate on the training-dev set.

0

1

Updated 2026-06-13

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