Prehistory — From Neural Networks to the TransformerKurt Hornik, Maxwell Stinchcombe, Halbert White
Multilayer feedforward networks are universal approximators
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Multilayer feedforward networks are universal approximators — extended the universal approximation theorem to general conditions
Why it matters
Together with Cybenko, established the foundation for the approximation capability of multilayer feedforward neural networks
Source — Primary sources first; secondary reports are labelled “Press”
Pressen.wikipedia.orghttps://en.wikipedia.org/wiki/Universal_approximation_theoremAdded in Week 35, 2026 · See that week
On the map — ⓪ Prehistory line
- Previous stopBackpropagation
- This recordMultilayer feedforward networks are universal approximators
- Next stopGradient-based learning applied to document recognition