Skip to content
Kudos AI
enfrar

Convolution as a Prior

Why a dense layer is the wrong tool for pixels, and what weight sharing and locality actually assume about images.

IntermediateModule 330 min · 120 XP
One 3×3 kernel swept across an image with the same nine weights lighting up at every stop - weight sharing as a claim about the world, not a saving.

This is a premium lesson

Sign in and enrol to read the full lesson, run the code, take the quiz, and earn XP toward the path badge.

Sign inCreate account
← Back to Deep Learning Foundations