arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.12682cs.LGstat.ML
收藏

Neural Dynamical Systems:物理预测中的结构和灵活性平衡

Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Prediction

Carnegie Mellon University(卡内基梅隆大学);Princeton Plasma Physics Laboratory(普林斯顿等离子体物理实验室)

Viraj Mehta, Ian Char, Willie Neiswanger, Youngseog Chung, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider

摘要:

我们介绍神经动力系统(NDS),学习动态模型的方法,在各种灰箱设置,其中包括先验知识的形式系统的常微分方程。NDS使用神经网络来估计系统的自由参数,预测残差项,并随时间进行数值积分以预测未来状态。一个关键的见解是,许多感兴趣的真实动态系统很难建模,因为动态可能会因部署而异。我们缓解这个问题,采取的轨迹先验状态作为输入NDS和训练它动态估计系统参数使用前的轨迹。我们发现,NDS学习动态具有更高的准确性和更少的样本比各种深度学习方法,不结合先验知识和方法从系统辨识文献。我们证明了这些优势,首先在合成动力系统,然后从氘枪从核聚变反应堆捕获的真实数据。最后,我们证明,这些好处可以用于控制在小规模的实验。

英文摘要:

We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models in various gray-box settings which incorporates prior knowledge in the form of systems of ordinary differential equations. NDS uses neural networks to estimate free parameters of the system, predicts residual terms, and numerically integrates over time to predict future states. A key insight is that many real dynamical systems of interest are hard to model because the dynamics may vary across rollouts. We mitigate this problem by taking a trajectory of prior states as the input to NDS and train it to dynamically estimate system parameters using the preceding trajectory. We find that NDS learns dynamics with higher accuracy and fewer samples than a variety of deep learning methods that do not incorporate the prior knowledge and methods from the system identification literature which do. We demonstrate these advantages first on synthetic dynamical systems and then on real data captured from deuterium shots from a nuclear fusion reactor. Finally, we demonstrate that these benefits can be utilized for control in small-scale experiments.

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。

↑