论文标题
参数变化的神经常见微分方程，并带有不合同网络
Parameter-varying neural ordinary differential equations with partition-of-unity networks
论文作者
论文摘要
在这项研究中，我们提出了与参数变化的神经差微分方程（节点），其中模型参数的演变由专家体系结构的混合物（PONETS）表示。与POUNET合成的节点的建议变体学习空间的无网格分区，并使用与每个分区相关的多项式来表示ODE参数的演变。我们证明了针对三个重要任务的提议方法的有效性：（1）混合系统的数据驱动的动力学建模，（2）切换线性动力学系统，以及（3）具有不同外部强迫的动力学系统的潜在动力学。
In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture. The proposed variant of NODEs, synthesized with POUNets, learn a meshfree partition of space and represent the evolution of ODE parameters using sets of polynomials associated to each partition. We demonstrate the effectiveness of the proposed method for three important tasks: data-driven dynamics modeling of (1) hybrid systems, (2) switching linear dynamical systems, and (3) latent dynamics for dynamical systems with varying external forcing.
