Prehistory — From Neural Networks to the TransformerGeorge Cybenko
Approximation by superpositions of a sigmoidal function
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Approximation by superpositions of a sigmoidal function — proved the universal approximation theorem
Why it matters
Proved that a single hidden layer can approximate any continuous function, providing a theoretical basis for expressive power
Source — Primary sources first; secondary reports are labelled “Press”
Paperlink.springer.comhttps://link.springer.com/article/10.1007/BF02551274Added in Week 35, 2026 · See that week
On the map — ⓪ Prehistory line
- Previous stopBackpropagation
- This recordApproximation by superpositions of a sigmoidal function
- Next stopGradient-based learning applied to document recognition