Some new results on neural network appro
โ
K. Hornik
๐
Article
๐
1993
๐
Elsevier Science
๐
English
โ 346 KB
We show that standardfeedforward networks with asl ew as a single hidden layer can uniformly approximate continuousfunctions on compacta provided that the activation function if; is locally R iemann integrable and nonpolynomial, and have universal LP(Jl) approximation capabilities for finite and com