# Generating Random Parameters in Feedforward Neural Networks with Random Hidden Nodes: Drawbacks of the Standard Method and How to Improve It

arXiv: https://arxiv.org/abs/1908.05864 · HTML: https://mlsanity.com/paper/1908.05864/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Randomized Neural Networks for Forecasting Time Series with Multiple Seasonality](https://mlsanity.com/paper/2107.01705/) (2021)
- [Ensembles of Randomized NNs for Pattern-based Time Series Forecasting](https://mlsanity.com/paper/2107.04091/) (2021)
- [Boosted Ensemble Learning based on Randomized NNs for Time Series Forecasting](https://mlsanity.com/paper/2203.00980/) (2022)
- [Data-Driven Learning of Feedforward Neural Networks with Different Activation Functions](https://mlsanity.com/paper/2107.01702/) (2021)
- [Autoencoder based Randomized Learning of Feedforward Neural Networks for Regression](https://mlsanity.com/paper/2107.01711/) (2021)
- [HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation](https://mlsanity.com/paper/2501.18199/) (2025)

## Abstract (arXiv)

The standard method of generating random weights and biases in feedforward neural networks with random hidden nodes, selects them both from the uniform distribution over the same fixed interval. In this work, we show the drawbacks of this approach and propose a new method of generating random parameters. This method ensures the most nonlinear fragments of sigmoids, which are most useful in modeling target function nonlinearity, are kept in the input hypercube. In addition, we show how to generate activation functions with uniformly distributed slope angles.