论文标题
过渡到通用神经网络的线性，并具有定向的无环形架构
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
论文作者
论文摘要
在本文中，我们表明，与任意定向的无环图相对应的前馈神经网络会在其“宽度”接近无穷大的情况下过渡到线性。这些通用网络的宽度的特征在于其神经元的最小值，除了输入和第一层。我们的结果确定了向线性过渡的基础数学结构，并概括了许多旨在表征过渡到标准体系结构神经切线内核的线性或恒定性的近期作品。
In this paper we show that feedforward neural networks corresponding to arbitrary directed acyclic graphs undergo transition to linearity as their "width" approaches infinity. The width of these general networks is characterized by the minimum in-degree of their neurons, except for the input and first layers. Our results identify the mathematical structure underlying transition to linearity and generalize a number of recent works aimed at characterizing transition to linearity or constancy of the Neural Tangent Kernel for standard architectures.
