Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings

Multilayer feedforward networks are universal approximators

Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations

Computing, Computer Science, Mathematics +10

Approximation by superpositions of a sigmoidal function

George Cybenko · Mathematics of Control Signals and Systems · 1989 · 13.7K citations

Computing, Computer Science, Machine Learning +5

Real and Complex Analysis.

G. A. Garreau, Walter Rudin · Journal of the Royal Statistical Society Series D (The Statistician) · 1987 · 11K citations

Natural Sciences, Mathematics, Probability Theory +16

Cross-Validatory Choice and Assessment of Statistical Predictions

M. Stone · Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1974 · 10.5K citations

Education, Data Science, Method Validation +9

Multilayer feedforward networks are universal approximators

HornikK., StinchcombeM., WhiteH. · Neural Networks · 1989 · 9.4K citations

Computing, Computer Science, Mathematics +10