Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data

TL;DR

This paper introduces a stochastic variational deep kernel learning approach that learns low-dimensional dynamical models from high-dimensional noisy data, effectively denoising, compressing, and modeling system evolution without labeled data.

Contribution

It presents a novel unsupervised framework combining deep kernel learning and variational methods for discovering dynamical models from complex noisy data.

Findings

Successfully denoises high-dimensional measurements

Learns compact low-dimensional state representations

Identifies and quantifies modeling uncertainties

Abstract

This work proposes a Stochastic Variational Deep Kernel Learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses high-dimensional measurements into low-dimensional state variables, and a latent dynamical model for the state variables that predicts the system evolution over time. The training of the proposed model is carried out in an unsupervised manner, i.e., not relying on labeled data. Our learning method is evaluated on the motion of a pendulum -- a well studied baseline for nonlinear model identification and control with continuous states and control inputs -- measured via high-dimensional noisy RGB images. Results show that the method can effectively denoise measurements, learn compact state representations and latent dynamical models, as well as identify and quantify modeling uncertainties.