ClassroomThe classroom
Back to the lesson libraryMATH SIDE LESSON
B07 A SMALL STEP SIDEWAYS

Follow shapes through a numerical layer

Nearly every layer in a neural network computes XW + b. Work one out by hand for two songs, then learn the shape rule that catches most bugs before they happen.

LESSON OVERVIEW10 min lesson

Lesson overview

Nearly every layer in a neural network computes XW + b. Work one out by hand for two songs, then learn the shape rule that catches most bugs before they happen.

What you’ll explore

  • Compute an entry of XW + b by hand, predict the shape of a matrix product, and explain why XW and WX usually differ.
GO TO THE SOURCE

Original explanations, connected to the research.

Dive into Deep Learning — linear algebra
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.