On the approximation by single hidden layer feedforward neural networks with fixed weights
Guliyev, Namig J.
Ismailov, Vugar E.
- Publisher: Elsevier
activation function | sigmoidal function | approximation | ACM : I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.6: Learning/I.2.6.2: Connectionism and neural nets | C.1.3 | 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] | I.2.6 | weight | [ INFO.INFO-NE ] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] | I.5.1 | [ INFO.INFO-IT ] Computer Science [cs]/Information Theory [cs.IT] | feedforward neural network | Computer Science - Information Theory | hidden layer | [ MATH.MATH-IT ] Mathematics [math]/Information Theory [math.IT] | 2010 MSC: 41A30, 41A63, 65D15, 68T05, 92B20 | 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 | 41A30, 41A63, 65D15, 68T05, 92B20 | 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) | F.1.1
arxiv: Quantitative Biology::Neurons and Cognition
International audience; Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the probability of the considered network to give precise results. In this note, we constructively prove that SLFNs with the fixed weight 1 and two neurons in the hidden layer can approximate any continuous function on a compact subset of the real line. The applicability of this result is demonstrated in various numerical examples. Finally, we show that SLFNs with fixed weights cannot approximate all continuous multivariate functions.