ClassroomThe classroom
Back to the lesson libraryMECHANISM · 14 MIN
M09.1 CONNECT THE MECHANISM

Will the model work on new examples?

A leaf-disease app gets all 2,000 of its training photos right, then misses one fresh leaf in five. Which number should you believe, and why do the two disagree?

LESSON OVERVIEW14 min lesson

Lesson overview

A leaf-disease app gets all 2,000 of its training photos right, then misses one fresh leaf in five. Which number should you believe, and why do the two disagree?

What you’ll explore

  • Empirical error measures observed examples, while expected error refers to a target distribution; generalization claims depend on sampling, selection, and task assumptions.
GO TO THE SOURCE

Original explanations, connected to the research.

An Introduction to Statistical Learning — authors’ materialsDive into Deep Learning — authors’ open textbookDo ImageNet Classifiers Generalize to ImageNet? (Recht et al., 2019)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.