# On the approximation by single hidden layer feedforward neural networks with fixed weights

arXiv: https://arxiv.org/abs/1708.06219 · HTML: https://mlsanity.com/paper/1708.06219/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2017.

## Built on by (most cited first, 19 of 19)

- [On the approximation of functions by tanh neural networks](https://mlsanity.com/paper/2104.08938/) (2021)
- [A Survey on Universal Approximation Theorems](https://mlsanity.com/paper/2407.12895/) (2024)
- [Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks](https://mlsanity.com/paper/2401.02277/) (2024)
- [Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis](https://mlsanity.com/paper/2410.02242/) (2024)
- [asKAN: Active Subspace embedded Kolmogorov-Arnold Network](https://mlsanity.com/paper/2504.04669/) (2025)
- [Universal approximation theorem for neural networks with inputs from a topological vector space](https://mlsanity.com/paper/2409.12913/) (2024)
- [Quantum advantage for learning shallow neural networks with natural data distributions](https://mlsanity.com/paper/2503.20879/) (2025)
- [Approximation error of single hidden layer neural networks with fixed weights](https://mlsanity.com/paper/2202.03289/) (2022)
- [Trainable and Explainable Simplicial Map Neural Networks](https://mlsanity.com/paper/2306.00010/) (2023)
- [Simmering: Sufficient is better than optimal for training neural networks](https://mlsanity.com/paper/2410.19912/) (2024)
- [Approximation properties of neural ODEs](https://mlsanity.com/paper/2503.15696/) (2025)
- [On shallow feedforward neural networks with inputs from a topological space](https://mlsanity.com/paper/2504.02321/) (2025)
- [XDT-CXR: Investigating Cross-Disease Transferability in Zero-Shot Binary Classification of Chest X-Rays](https://mlsanity.com/paper/2408.11493/) (2024)
- [Numerical Approximation Capacity of Neural Networks with Bounded Parameters: Do Limits Exist, and How Can They Be Measured?](https://mlsanity.com/paper/2409.16697/) (2024)
- [On Explicit Super-Expressive Approximation for Neural Networks](https://mlsanity.com/paper/2607.06781/) (2026)
- [Learnability of high-dimensional targets by two-parameter models and gradient flow](https://mlsanity.com/paper/2402.17089/) (2024)
- [Activation Bottleneck: Sigmoidal Neural Networks Cannot Forecast a Straight Line](https://mlsanity.com/paper/2406.02146/) (2024)
- [Universal Approximation Theorem for Input-Connected Multilayer Perceptrons](https://mlsanity.com/paper/2601.14026/) (2026)
- [Universality of shallow and deep neural networks on non-Euclidean spaces](https://mlsanity.com/paper/2602.23381/) (2026)

## Abstract (arXiv)

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.