Cargando…

Deep kernel learning of dynamical models from high-dimensional noisy data

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Botteghi, Nicolò, Guo, Mengwu, Brune, Christoph
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9747975/
https://www.ncbi.nlm.nih.gov/pubmed/36513711
http://dx.doi.org/10.1038/s41598-022-25362-4
_version_ 1784849723480342528
author Botteghi, Nicolò
Guo, Mengwu
Brune, Christoph
author_facet Botteghi, Nicolò
Guo, Mengwu
Brune, Christoph
author_sort Botteghi, Nicolò
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9747975
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-97479752022-12-15 Deep kernel learning of dynamical models from high-dimensional noisy data Botteghi, Nicolò Guo, Mengwu Brune, Christoph Sci Rep Article 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. Nature Publishing Group UK 2022-12-13 /pmc/articles/PMC9747975/ /pubmed/36513711 http://dx.doi.org/10.1038/s41598-022-25362-4 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Botteghi, Nicolò
Guo, Mengwu
Brune, Christoph
Deep kernel learning of dynamical models from high-dimensional noisy data
title Deep kernel learning of dynamical models from high-dimensional noisy data
title_full Deep kernel learning of dynamical models from high-dimensional noisy data
title_fullStr Deep kernel learning of dynamical models from high-dimensional noisy data
title_full_unstemmed Deep kernel learning of dynamical models from high-dimensional noisy data
title_short Deep kernel learning of dynamical models from high-dimensional noisy data
title_sort deep kernel learning of dynamical models from high-dimensional noisy data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9747975/
https://www.ncbi.nlm.nih.gov/pubmed/36513711
http://dx.doi.org/10.1038/s41598-022-25362-4
work_keys_str_mv AT botteghinicolo deepkernellearningofdynamicalmodelsfromhighdimensionalnoisydata
AT guomengwu deepkernellearningofdynamicalmodelsfromhighdimensionalnoisydata
AT brunechristoph deepkernellearningofdynamicalmodelsfromhighdimensionalnoisydata