Short Answer

Human-label tasks for estimating the best possible error

Question: According to the lesson, what are two example tasks that people can do well enough to use human labels when estimating the optimal error rate?

Sample answer: Two examples are identifying common objects in clear photographs and transcribing short, clean speech clips.

Key points:

  • Identifying common objects in clear photographs
  • Transcribing short, clean speech clips

Rubric: Award full credit if the student gives both examples of tasks that humans can perform reasonably well.

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