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

Autor:	Pinto, Rafael C., Tavares, Anderson R.
Rok vydání:	2024
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.10821 Zobrazit plný text záznamu View this record from Arxiv