Variational Integrator Networks for Physically Meaningful Embeddings

by   Steindór Sæmundsson, et al.

Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas. By leveraging recent work connecting deep neural networks to systems of differential equations, we propose variational integrator networks, a class of neural network architectures designed to ensure faithful representations of the dynamics under study. This class of network architectures facilitates accurate long-term prediction, interpretability, and data-efficient learning, while still remaining highly flexible and capable of modeling complex behavior. We demonstrate that they can accurately learn dynamical systems from both noisy observations in phase space and from image pixels within which the unknown dynamics are embedded.


page 1

page 2

page 3

page 4


Learning Contact Dynamics using Physically Structured Neural Networks

Learning physically structured representations of dynamical systems that...

State Space Representations of Deep Neural Networks

This paper deals with neural networks as dynamical systems governed by d...

Variability of echo state network prediction horizon for partially observed dynamical systems

Study of dynamical systems using partial state observation is an importa...

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems

Given an unknown dynamical system, what is the minimum number of samples...

Tangent-Space Regularization for Neural-Network Models of Dynamical Systems

This work introduces the concept of tangent space regularization for neu...

CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels

For systems with only known pixels, it is difficult to identify its dyna...

VPNets: Volume-preserving neural networks for learning source-free dynamics

We propose volume-preserving networks (VPNets) for learning unknown sour...

Code Repositories



view repo

Please sign up or login with your details

Forgot password? Click here to reset