Short Answer

What metric goes on the y-axis of a learning curve built from different training-set sizes?

Question: Explain how to determine the y-axis values when drawing a learning curve for several training-set sizes.

Sample answer: Use the development-set error. Train a separate copy of the model on each training-set size, then evaluate each trained model on the dev set and record that error.

Key points:

  • The y-axis is dev-set error.
  • Each point comes from a model trained on one training-set size and evaluated on the dev set.

Rubric: The response must name dev-set error as the y-axis quantity and state that each value is obtained by evaluating the model trained at that particular training-set size on the dev set.

0

1

Updated 2026-08-12

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