BriefGPT.xyz
May, 2023
神经常微分方程和深度残差网络的泛化界
Generalization bounds for neural ordinary differential equations and deep residual networks
HTML
PDF
Pierre Marion
TL;DR
本文研究基于连续时间参数的ODE类模型及其泛化界限，并探讨其与深度残差网络的类比关系，说明权重矩阵之间的差异对于神经网络的泛化能力有何影响。
Abstract
neural ordinary differential equations
(neural ODEs) are a popular family of
continuous-depth deep learning
models. In this work, we consider a large family of parameterized ODEs with continuous-in-time parameter
→