Filters and Convolutions

3 min
Audience
ages 10–15
Duration
30 to 40 min
Adventure
5/8
Badge to earn
Convolution Operator

Today's mission

Slide a 3 × 3 kernel, compute an activation map and explain weight sharing.

Proof of success: explain "Filters and convolutions", complete "The Sliding Filter" and name the limit of the analogy.

The story

In a black-and-white mosaic, Yara looks for vertical edges. She places a small 3 × 3 filter on the top-left corner, multiplies cell by cell, adds them, then moves the same filter. The strong responses form a new grid. Because the nine filter values are reused everywhere, the detector looks for the same pattern at every position. Convolution thus exploits locality and shares its parameters.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Images and Sound” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one