Learning dynamical models from the data is a fundamental process in science and engineering. System identification is the problem of building dynamical models from measured data of temporal signals in order to determine predictive relationships between them. The identified models can be used for forecasting the future outputs of the system, predicting responses to new input signals, or controlling the system. Satisfactorily solving this challenging problem requires flexible modeling tools that allow to incorporate structural knowledge that is specific of dynamical systems, as well as efficient computational techniques that are able to handle complex datasets. The machine learning community has been producing a large amount of modeling techniques for structured and large scale data that may potentially have a tremendous impact in the field of dynamical system identification.

This workshop aims at bringing together researchers from machine learning and system identification communities to foster discussion and elicit open problems on modeling and identification of dynamical systems. The workshop will consist of invited talks, contributed presentations, and posters. We plan to include an opening tutorial on system identification and an overview of the state-of-the-art techniques. Invited talks will be given by leading experts from both machine learning and system identification communities.

Confirmed speakers

  • Byron Boots, Carnegie Mellon University
  • Tianshi Chen, Linköping University
  • Alessandro Chiuso, University of Padova
  • Marc Deisenroth, Technische Universität Darmstadt
  • Giuseppe De Nicolao, University of Pavia
  • Håkan Hjalmarsson, KTH - Royal Institute of Technology
  • Lennart Ljung, Linköping University
  • Henrik Ohlsson, University of California, Berkeley
  • Necmiye Ozay, California Institute of Technology
  • Cristian Rojas, KTH - Royal Institute of Technology
  • Thomas Schön, Linköping University
  • Marco Signoretto, Katholieke Universiteit Leuven
  • Mario Sznaier, Northeastern University,
  • Lieven Vandenberghe, University of California, Los Angeles

Call for Posters and Papers

We solicit submission of extendend abstracts or papers discussing high quality research on all aspects of dynamical system modeling and identification with machine learning tools. Both theoretical and applied contributions presenting recent or ongoing research are welcomed. The list of tools, problems, and applications includes, but is not limited to the following

A one-page extended abstract suffices for a poster submission. Additionally, we welcome position papers, as well as papers discussing open problems and potential future research directions. Both extended abstracts and position/future research papers will be reviewed by program committee members on the basis of relevance, significance, and clarity. Submissions should be formatted according to the ICML 2013 conference template. The length of abstracts and papers should not exceed 8 pages.

Submission website

Important Dates

  • Apr 10, 2013 - Deadline of Submission (Extended from Mar 20, 2013)
  • Apr 15, 2013 - Notification of Acceptance
  • May 15, 2013 - Submission of Final Version
  • June 20-21, 2013 - Workshop

Venue and Registration

This workshop is co-located with the 30th International Conference on Machine Learning. For information about the venue, please visit the ICML 2013 website.

All participants need to register. Information about registration and fees can be found here .