Symplectic Recurrent Neural Networks

Zhengdao Chen, Jianyu Zhang, Martin Arjovsky, Léon Bottou

Keywords: optimization, rnn

Wednesday: Sequence Representations

Abstract: We propose Symplectic Recurrent Neural Networks (SRNNs) as learning algorithms that capture the dynamics of physical systems from observed trajectories. SRNNs model the Hamiltonian function of the system by a neural networks, and leverage symplectic integration, multiple-step 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. Finally, we show how to augment the SRNN integration scheme in order to handle stiff dynamical systems such as bouncing billiards.

Similar Papers

Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty,
Hamiltonian Generative Networks
Peter Toth, Danilo J. Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins,