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.
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.
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 oneThe 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.