将激活与计算合为一体，提升神经网络训练效率。
APTx Neuron: A Unified Trainable Neuron Architecture Integrating Activation and Computation
- 统一设计神经元，激活与线性变换整合为可训练表达式
- 在MNIST上11轮内达96.69%准确率，仅需33.2万参数
- 适合追求高效模型结构的深度学习研究者
我们提出APTx Neuron，一种新型统一神经计算单元，将非线性激活与线性变换整合为单一可训练表达式。该神经元源自APTx激活函数，无需独立激活层，使架构更优化且简洁。其函数形式为 $y = \ sum_{i=1}^{n} ((α_i + \tanh(β_i x_i)) \cdot γ_i x_i) + δ$，所有参数 $α_i$, $β_i$, $γ_i$, $δ$ 均可训练。我们在MNIST数据集上验证基于APTx Neuron的架构，在约33.2万可训练参数下，11个训练周期内达到最高96.69%测试准确率。结果表明，相较于传统神经元，APTx Neuron具备更强表达力与训练效率，预示着统一神经元设计的新范式。源代码见 https://github.com/mr-ravin/aptx_neuron。
原文摘要 · Abstract (English)
We propose the APTx Neuron, a novel, unified neural computation unit that integrates non-linear activation and linear transformation into a single trainable expression. The APTx Neuron is derived from the APTx activation function, thereby eliminating the need for separate activation layers and making the architecture both optimization-efficient and elegant. The proposed neuron follows the functional form $y = \sum_{i=1}^{n} ((α_i + \tanh(β_i x_i)) \cdot γ_i x_i) + δ$, where all parameters $α_i$, $β_i$, $γ_i$, and $δ$ are trainable. We validate our APTx Neuron-based architecture on the MNIST dataset, achieving up to $96.69\%$ test accuracy within 11 epochs using approximately 332K trainable parameters. The results highlight the superior expressiveness and training efficiency of the APTx Neuron compared to traditional neurons, pointing toward a new paradigm in unified neuron design and the architectures built upon it. Source code is available at https://github.com/mr-ravin/aptx_neuron.
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。