G. Cybenko (1989)
Mathematics of Control, Signals, and Systems, 2(4), 303-314.
DOI: https://doi.org/10.1007/bf02551274
Abstract. Proves the universal approximation theorem: a feedforward network with a single hidden layer of sigmoidal units can approximate any continuous function on a compact set to arbitrary accuracy, providing the theoretical basis for the expressive power of neural networks.
Tags: neural-networks theory universal-approximation