OBJECT RECORD / AIM-DOC-1986-001

Learning representations by back-propagating errors

A concise account of adjusting network weights by propagating output error backward.

CURATORIAL READING

Why it is here

Rumelhart, Hinton, and Williams described repeatedly changing connection weights to reduce the difference between actual and desired outputs, allowing hidden units to acquire useful task features.

Evidence boundary

The object documents one influential 1986 formulation. It does not establish that every later learning system uses the same procedure, or that the authors invented every ingredient.

05 / LEARN REPRESENTATIONS

Position in the guided path

From written rules to learned representations

Weights change as output error travels backward through the network.

Back to the object room →

PROVENANCE

Source trail