CoChat

Learning deep dynamical models from image pixels

Open access
Wahlström, Niklas, Schön, Thomas B, Deisenroth, Marc Peter · 2015 · IFAC-PapersOnLine
Cited by 58

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Abstract

Modeling dynamical systems is important in many disciplines, such as control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement mapping and the transition mapping (system dynamics) in latent space can be challenging. For linear system dynamics and measurement mappings efficient solutions for system identification are available. However, in practical applications, the linearity assumptions does not hold, requiring nonlinear system identification techniques. If additionally the observations are high-dimensional (e.g., images), nonlinear system identification is inherently hard. To address the problem of nonlinear system identification from high-dimensional observations, we combine recent advances in deep learning and system identification. In particular, we jointly learn a low-dimensional embedding of the observation by means of deep auto-encoders and a predictive transition model in this low-dimensional space. We demonstrate that our model enables learning good predictive models of dynamical systems from pixel information only.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.ifacol.2015.12.271

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 2 references

Research works printed but not linked: 15

  1. Bourlard, 1988, Auto-association by multilayer perceptrons and singular value decomposition., Biological cybernetics, 59, 291, 10.1007/BF00332918 · DOI · Paper page
  2. Deisenroth, 2015, Gaussian processes for data-efficient learning in robotics and control., IEEE Transaction on Pattern Analysis and Machine Intelligence, 37, 408, 10.1109/TPAMI.2013.218 · DOI · Paper page
  3. Doretto, 2003, Dynamic textures., International Journal of Computer Vision, 51, 91, 10.1023/A:1021669406132 · DOI · Paper page
  4. Ghahramani, Z. (1998). Learning dynamic bayesian networks. In C. Giles and M. Gori (eds.), Adaptive Processing of Sequences and Data Structures, volume 1387 of Lecture Notes in Computer Science, 168-197. Springer. · DOI · Paper page
  5. Gibson, 2005, Robust maximumlikelihood estimation of multivariable dynamic systems., Automatica, 41, 1667, 10.1016/j.automatica.2005.05.008 · DOI · Paper page
  6. Hinton, 2006, Reducing the dimensionality of data with neural networks., Science, 313, 504, 10.1126/science.1127647 · DOI · Paper page
  7. Kantas, N., Doucet, A., Singh, S.S., Maciejowski, J., and Chopin, N. (2015). On particle methods for parameter estimation in state-space models. Statistical Science. Accepted for publication. · doi:10.1214/14-sts511
  8. Ljung, L. (1999). System identification, Theory for the user. System sciences series. Prentice Hall, Upper Saddle River, NJ, USA, second edition.
  9. Nocedal, J. and Wright, S.J. (2006). Numerical Optimization. Springer Series in Operations Research. New York, USA, 2 edition.
  10. Schneider, 1997, Exploiting model uncertainty estimates for safe dynamic control learning., In NIPS
  11. Schön, 2011, System identification of nonlinear state-space models., Automatica, 47, 39, 10.1016/j.automatica.2010.10.013 · DOI · Paper page
  12. Shumway, 1982, An approach to time series smoothing and forecasting using the EM algorithm., Journal of Time Series Analysis, 3, 253, 10.1111/j.1467-9892.1982.tb00349.x · DOI · Paper page
  13. Sjöberg, 1995, Nonlinear black-box modeling in system identification: a unified overview., Automatica, 31, 1691, 10.1016/0005-1098(95)00120-8 · DOI · Paper page
  14. Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (ICML). Helsinki, Finland. · DOI · Paper page
  15. Wahlström, N., Schön, T.B., and Deisenroth, M.P. (2015). From pixels to torques: Policy learning with deep dynamical models. Preprint, arXiv:1502.02251. · arXiv

Cited by

See all 58

Metadata

Authors
Wahlström, N., Schön, T. B., & Deisenroth, M. P.
Venue
IFAC-PapersOnLine
Publisher
Elsevier BV
Published
2015
Volume
48
Issue
28
Pages
1059-1064
ISSN
2405-8963 (ISSN-L)
OpenAlex
W2137376508
Cited by
58
References
2
FWCI
5.88
Type
journal article
Language
en
Open access
diamond
Licence
www.elsevier.com/tdm/userlicense/1.0/ (tdm)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Learning deep dynamical models from image pixels. https://app.cochat.ai/papers/10.1016/j.ifacol.2015.12.271
The paper
Wahlström, N., Schön, T. B., & Deisenroth, M. P. (2015). Learning deep dynamical models from image pixels. IFAC-PapersOnLine. https://doi.org/10.1016/j.ifacol.2015.12.271

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.