Why Depth Works: Folding Space and Reusing Features

How a network computes, why gradients vanish, and what makes depth trainable

dl.5 already told you that one hidden layer is enough. Given enough units, a single layer can approximate any continuous function on an interval as closely as you like. So the question this whole course has been putting off: why stack layers at all?

๐Ÿ”’ This is a Pro lesson โ€” the interactive figure, worked examples, quiz and practice open with Pro access.

โ–ถ Why Depth Works: Folding Space and Reusing Features
โ† Gradient Noise Scale: Why ฮท and B Are One KnobBridge: Weight Sharing, Convolution and Attention โ†’