Machine learning
Neural ODE
一种神经常微分方程（Neural ODE）由 Chen 及其同事于 2018 年提出，它将隐藏状态建模为常微分方程的连续解，而该方程的动力学由神经网络参数化。它推广了残差连接的极限情况，因此非常适合不规则采样的时间序列和基于物理的建模。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Chen, T. Q., Rubanova, Y., Bettencourt, J. & Duvenaud, D. (2018). Neural Ordinary Differential Equations. Advances in Neural Information Processing Systems (NeurIPS). link ↗
- Rubanova, Y., Chen, T. Q. & Duvenaud, D. (2019). Latent ODEs for Irregularly-Sampled Time Series. Advances in Neural Information Processing Systems (NeurIPS). link ↗
如何引用本页
ScholarGate. (2026, June 1). Neural Ordinary Differential Equation. ScholarGate. https://scholargate.app/zh/deep-learning/neural-ode
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →