On the approximation by single hidden layer feedforward neural networks with fixed weights
This provides a theoretical foundation for simplifying neural network architectures in univariate function approximation, though it is incremental as it builds on prior work about fixed-weight networks.
The paper proves that single hidden layer feedforward neural networks with fixed weights and only two hidden neurons can approximate any continuous univariate function on a compact set, and demonstrates this with numerical examples, while also showing that such networks cannot approximate all multivariate continuous functions.
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.