## A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function

*Guliyev , Namig*;

*Ismailov , Vugar*;

- Publisher: Massachusetts Institute of Technology Press (MIT Press)
Related identifiers: - Subject: Sigmoidal functions | λ-monotonicity | Continued fractions | ACM : I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.6: Learning/I.2.6.2: Connectionism and neural nets | 41A30, 65D15, 92B20 | ACM : I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.1: Models/I.5.1.3: Neural nets | [ MATH.MATH-NA ] Mathematics [math]/Numerical Analysis [math.NA] | Bernstein polynomials | [ INFO.INFO-NE ] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] | Calkin--Wilf sequence | [ INFO.INFO-IT ] Computer Science [cs]/Information Theory [cs.IT] | Smooth transition function | Computer Science - Information Theory | [ MATH.MATH-IT ] Mathematics [math]/Information Theory [math.IT] | Computer Science - Neural and Evolutionary Computing | ACM : C.: Computer Systems Organization/C.1: PROCESSOR ARCHITECTURES/C.1.3: Other Architecture Styles/C.1.3.7: Neural nets | Mathematics - Numerical Analysis | ACM : F.: Theory of Computation/F.1: COMPUTATION BY ABSTRACT DEVICES/F.1.1: Models of Computation/F.1.1.4: Self-modifying machines (e.g., neural networks)

The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can approximate an arbitrary continuous fu... View more

Share - Bookmark

- Download from