Essay

How to build a dev-set error curve from different training set sizes

Question: Explain how to construct a curve that shows dev-set error as the amount of training data changes. Describe how to train the models, what results to record, and how to place the values on the graph.

Sample answer: To build the curve, train the same learning algorithm multiple times using different training-set sizes. For example, with 2,000 training examples, you might fit separate models on 200, 400, 800, 1,200, and 2,000 examples. After each model is trained, evaluate it on the dev set and record the dev-set error. Then draw the graph with training-set size on the x-axis and dev-set error on the y-axis so you can see how performance changes as more data is used.

Key points:

  • Train separate copies of the model on different training-set sizes.
  • Measure dev-set error for each trained model.
  • Plot training-set size on the x-axis and dev-set error on the y-axis.

Rubric: The answer must include: 1) training separate copies of the model on different training-set sizes, 2) measuring dev-set error for each copy, and 3) plotting dev-set error versus training-set size with the correct axes.

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