单层PReLU网络可完美解决异或问题，且更稳定高效。
PReLU: Yet Another Single-Layer Solution to the XOR Problem
- 用可学习参数的PReLU激活函数构造单层网络
- 在更广学习率范围内达100%准确率，仅需3个可训练参数
- 相比多层网络和新激活函数，性能更优且结构更简单
本文证明使用可参数化修正线性单元（PReLU）激活函数的单层神经网络能够解决异或（XOR）问题，这一简单事实此前一直被忽视。我们将其与多层感知机（MLP）及增长余弦单元（GCU）激活函数进行比较，并解释了为何PReLU具备此能力。实验结果表明，单层PReLU网络在更广泛的学习率范围内均可实现100%的成功率，且仅需三个可学习参数。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。