资源分类
》 资源 》论文》Symplectic Recurrent Neural Networks

Symplectic Recurrent Neural Networks

2019-12-30 | |  104 |   46 |   0

Abstract

We propose Symplectic Recurrent Neural Networks (SRNNs) as learning algorithms that capture the dynamics of physical systems from observed trajectories. An SRNN models the Hamiltonian function of the system by a neural network and furthermore leverages symplectic integration, multiplestep training and initial state optimization to address the challenging numerical issues associated with Hamiltonian systems. We show SRNNs succeed reliably on complex and noisy Hamiltonian systems. We also show how to augment the SRNN integration scheme in order to handle stiff dynamical systems such as bouncing billiards.

上一篇：GRAPH NEURAL NETWORKS EXPONENTIALLY LOSEE XPRESSIVE POWER FOR NODE CLASSIFICATION

下一篇：TOWARDS NEURAL NETWORKS THAT PROVABLY KNOWWHEN THEY DON ’T KNOW

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...