Deep Representation Learning for Dynamical Systems Modeling

02/10/2020
by   Anna Shalova, et al.
0

Proper states' representations are the key to the successful dynamics modeling of chaotic systems. Inspired by recent advances of deep representations in various areas such as natural language processing and computer vision, we propose the adaptation of the state-of-art Transformer model in application to the dynamical systems modeling. The model demonstrates promising results in trajectories generation as well as in the general attractors' characteristics approximation, including states' distribution and Lyapunov exponent.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2020

Tensorized Transformer for Dynamical Systems Modeling

The identification of nonlinear dynamics from observations is essential ...
research
01/31/2023

Continuous Spatiotemporal Transformers

Modeling spatiotemporal dynamical systems is a fundamental challenge in ...
research
09/02/2022

Introducing dynamical constraints into representation learning

While representation learning has been central to the rise of machine le...
research
08/25/2023

In-context learning for model-free system identification

In traditional system identification, we estimate a model of an unknown ...
research
05/12/2022

Predictability Exponent of Stochastic Dynamical Systems

Predicting the trajectory of stochastic dynamical systems (SDSs) is an i...
research
10/27/2017

Multi-level Residual Networks from Dynamical Systems View

Deep residual networks (ResNets) and their variants are widely used in m...
research
11/14/2018

Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems

Filtering is a general name for inferring the states of a dynamical syst...

Please sign up or login with your details

Forgot password? Click here to reset