Prehistory — From Neural Networks to the TransformerDavid Rumelhart, Geoffrey Hinton, Ronald WilliamsGeoffrey Hinton
Learning representations by back-propagating errors
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Learning representations by back-propagating errors — Nature 323(6088) 533–536
Why it matters
Showed that hidden layers learn useful internal representations for a task on their own, making the training of multilayer neural networks practical
Source — Primary sources first; secondary reports are labelled “Press”
Papernature.comhttps://www.nature.com/articles/323533a0Added in Week 35, 2026 · See that week
On the map — ⓪ Prehistory line
- Previous stopWerbos's Harvard PhD thesis describes backpropagation for multilayer networks
- This record · stopBackpropagation
- Next stopGradient-based learning applied to document recognition