Adam

How models actually learn, from vanilla gradient descent to Adam

Adam combines two ideas: momentum for the average gradient, and RMSProp-style scaling for the average squared gradient. It then corrects early bias because those moving averages start at zero.

🔒 This is a Pro lesson — the interactive figure, worked examples, quiz and practice open with Pro access.

▶ Adam
← RMSPropStochastic & Mini-Batch GD →