Forecasting Sequential Data using Consistent Koopman Autoencoders
Forecasting Sequential Data using Consistent Koopman Autoencoders
复制标题
DOI：
--
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
Omri Azencot;N. Benjamin Erichson;Vanessa Lin;Michael W. Mahoney
中科院分区：
文献类型：
--
作者：
Omri Azencot;N. Benjamin Erichson;Vanessa Lin;Michael W. Mahoney
递归神经网络广泛用于时间序列数据，但这种模型往往忽略了这些序列中的底层物理结构。介绍了一类与Koopman理论相关的新的基于物理的方法，为处理非线性动力系统提供了一种选择。在这项工作中，我们提出了一种新的一致Koopman自动编码器模型，与大多数现有的工作不同，它利用了向前和向后的动态。我们的方法的关键是一个新的分析，探讨一致的动态和相关的Koopman运营商之间的相互作用。我们的网络与衍生分析直接相关，其计算要求与其他基线相当。我们在广泛的高维和短期相关问题上评估了我们的方法，它实现了对重要预测范围的准确估计，同时对噪音也具有鲁棒性。
Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators. Our network is directly related to the derived analysis, and its computational requirements are comparable to other baselines. We evaluate our method on a wide range of high-dimensional and short-term dependent problems, and it achieves accurate estimates for significant prediction horizons, while also being robust to noise.