提出模糊顶点池化，提升神经网络早期训练效率
Architectural change in neural networks using fuzzy vertex pooling
- 引入模糊顶点池化框架，动态聚合网络顶点
- 初期训练损失下降快，参数少仍保持高精度
- 适合深度模型初期训练，长期或大数据下效果减弱
顶点池化通过创建新顶点并连接原端点邻接节点，随后移除原端点及其边来实现。本文提出模糊顶点池化（FVP）的正式框架，分析其关键性质并应用于神经网络。实验表明，该模型在减少隐藏层神经元数量的同时，能快速降低损失并维持竞争性准确率。然而，在长时间训练或大规模数据下，性能逐渐下降，说明池化在深度学习后期阶段效果减弱。因此，建议将池化作为先进深度模型早期训练策略，以发挥其初始效率优势。
原文摘要 · Abstract (English)
The process of pooling vertices involves the creation of a new vertex, which becomes adjacent to all the vertices that were originally adjacent to the endpoints of the vertices being pooled. After this, the endpoints of these vertices and all edges connected to them are removed. In this document, we introduce a formal framework for the concept of fuzzy vertex pooling (FVP) and provide an overview of its key properties with its applications to neural networks. The pooling model demonstrates remarkable efficiency in minimizing loss rapidly while maintaining competitive accuracy, even with fewer hidden layer neurons. However, this advantage diminishes over extended training periods or with larger datasets, where the model's performance tends to degrade. This study highlights the limitations of pooling in later stages of deep learning training, rendering it less effective for prolonged or large-scale applications. Consequently, pooling is recommended as a strategy for early-stage training in advanced deep learning models to leverage its initial efficiency.
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。