← Back to timeline
Deep Learning1986demo planned

Backpropagation

MLP and chain rule

Backprop made deep networks trainable by pushing error signals backward through each layer.

Roadmap node · demo on the way

Read the wiki entry for Backpropagation

The interactive demo for this model is on the build list — the live linear regression demo is the template the rest will follow. The wiki entry already has the full concept, history, and where this fits in the chain.