Short Answer

What should a team do after the development set stops guiding decisions?

Question: A machine learning team notices that its development set and evaluation metric are no longer useful for choosing models because the team has started fitting the development set too closely. What action should they take?

Sample answer: They should refresh the development set by collecting additional development examples.

Key points:

  • The problem is that the team has adapted too much to the current development set.
  • The fix is to expand or replace it with more development data.

Rubric: The answer must state that the team should obtain more development set data to address the overfitting problem.

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

Related