arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.13262cs.LGstat.ML
收藏

调制神经常微分方程

Modulated Neural ODEs

University of Amsterdam(阿姆斯特丹大学);University of Tübingen(图宾根大学);Tübingen AI Center(图宾根人工智能中心);MIT-IBM Watson AI Lab(MIT-IBM沃森人工智能实验室)

Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

AI总结:

本文提出调制神经常微分方程(MoNODE),通过引入时间不变调制变量区分动力学状态与静态变化因素,改进现有NODE方法,提升泛化与远距离预测能力。

摘要:

神经常微分方程(NODEs)已被证明在学习任意轨迹的非线性动力学方面非常有用。然而,当前的NODE方法仅通过初始状态值或自回归编码器更新来捕捉不同轨迹之间的变化。在这项工作中,我们引入了调制神经常微分方程(MoNODEs),这是一种新颖的框架,将动力学状态与潜在的静态变化因素区分开来,并改进了现有的NODE方法。具体而言,我们引入了从数据中学习的\textit{时间不变调制变量}。我们将我们提出的框架整合到四种现有的NODE变体中。我们在振荡系统、视频和人类行走轨迹上测试了MoNODE,其中每条轨迹具有特定于轨迹的调制。我们的框架持续改进了现有模型泛化到新的动态参数化以及进行远距离预测的能力。此外,我们验证了所提出的调制变量确实能反映真实的未知变化因素,以$R^2$分数衡量。

英文摘要:

Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories. However, current NODE methods capture variations across trajectories only via the initial state value or by auto-regressive encoder updates. In this work, we introduce Modulated Neural ODEs (MoNODEs), a novel framework that sets apart dynamics states from underlying static factors of variation and improves the existing NODE methods. In particular, we introduce $\textit{time-invariant modulator variables}$ that are learned from the data. We incorporate our proposed framework into four existing NODE variants. We test MoNODE on oscillating systems, videos and human walking trajectories, where each trajectory has trajectory-specific modulation. Our framework consistently improves the existing model ability to generalize to new dynamic parameterizations and to perform far-horizon forecasting. In addition, we verify that the proposed modulator variables are informative of the true unknown factors of variation as measured by $R^2$ scores.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑