English

PReLU: Yet Another Single-Layer Solution to the XOR Problem

Neural and Evolutionary Computing 2024-09-18 v1 Artificial Intelligence Machine Learning

Abstract

This paper demonstrates that a single-layer neural network using Parametric Rectified Linear Unit (PReLU) activation can solve the XOR problem, a simple fact that has been overlooked so far. We compare this solution to the multi-layer perceptron (MLP) and the Growing Cosine Unit (GCU) activation function and explain why PReLU enables this capability. Our results show that the single-layer PReLU network can achieve 100\% success rate in a wider range of learning rates while using only three learnable parameters.

Keywords

Cite

@article{arxiv.2409.10821,
  title  = {PReLU: Yet Another Single-Layer Solution to the XOR Problem},
  author = {Rafael C. Pinto and Anderson R. Tavares},
  journal= {arXiv preprint arXiv:2409.10821},
  year   = {2024}
}
R2 v1 2026-06-28T18:47:06.924Z