# Improving Randomized Learning of Feedforward Neural Networks by Appropriate Generation of Random Parameters

## TL;DR

This paper proposes a novel method for generating random parameters in single-hidden-layer neural networks, improving learning performance by strategically selecting and rotating activation functions to better approximate complex target functions.

## Contribution

The paper introduces a new approach for random parameter generation that enhances the approximation capabilities of randomized neural networks compared to traditional fixed-interval methods.

## Key findings

- Better approximation of complex functions
- Avoids saturation of activation functions
- Improves learning outcomes in randomized neural networks

## Abstract

In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions from an interval adjusted to the target function, then randomly rotates the activation functions, and finally distributes them across the input space. For complex target functions the proposed method gives better results than the approach commonly used in practice, where the random parameters are selected from the fixed interval. This is because it introduces the steepest fragments of the activation functions into the input hypercube, avoiding their saturation fragments.