ClassroomThe classroom
Back to the lesson libraryMATH SIDE LESSON
B13 A SMALL STEP SIDEWAYS

Several inputs, several rates of change

A network's loss depends on millions of weights at once. Learn how to ask each weight separately "which way, and how fast?", and why the answers form a gradient.

LESSON OVERVIEW9 min lesson

Lesson overview

A network's loss depends on millions of weights at once. Learn how to ask each weight separately "which way, and how fast?", and why the answers form a gradient.

What you’ll explore

  • Partial derivatives isolate one input’s local effect; gradients collect scalar sensitivities, while Jacobians organize sensitivities for vector outputs.
GO TO THE SOURCE

Original explanations, connected to the research.

Deep Learning — linear algebraDive into Deep Learning — multivariable calculus
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.