Encyclopedia of the Sciences of Learning

2012 Edition
| Editors: Norbert M. Seel

Approximate Learning of Dynamic Models/Systems

  • Bhaskar DasGuptaEmail author
  • Derong Liu
Reference work entry
DOI: https://doi.org/10.1007/978-1-4419-1428-6_82



Dynamical systems model the evolution of a system with unknown parameters. The goal of a learning procedure is to estimate the parameters of the system, possibly from a set of known examples, such that the system behavior on future inputs is accurately predicted. Such a learning procedure typically uses methodologies from techniques in statistics and computer science and can be computationally intractable for some systems.

Theoretical Background

A dynamical system models the state-space evolution of a system. In the discussion below, we refer to free parameter that models the change in dynamics by “time.” Many versions of such systems are possible, depending on whether the state variables are continuous or discrete (quantitative), the time variables are continuous (e.g., partial differential equation, delay equations) or discrete (e.g., difference equations, quantized descriptions of continuous...
This is a preview of subscription content, log in to check access.


  1. Barron, A. R. (1991). Approximation and estimation bounds for artificial neural networks. In Proceedings of the 4th Annual Workshop on Computational Learning Theory (pp. 243–249). San Francisco: Morgan Kaufmann.Google Scholar
  2. Kearns, M. J., & Vazirani, U. V. (1994). An introduction to computational learning theory. Cambridge: MIT Press.Google Scholar
  3. Kolmogorov, A. N. (1957). On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition. Doklady Akademii. Nauk SSSR, 114, 953–956.Google Scholar
  4. Sontag, E. D. (1998). Mathematical control theory: Deterministic finite dimensional systems (2nd ed.). New York: Springer.Google Scholar
  5. Sontag, E. D. (2005). Molecular systems biology and control. European Journal of Control, 11(4-5), 396–435.Google Scholar
  6. Vapnik, V. N. (1982). Estimation of dependencies based on empirical data. Berlin: Springer.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of IllinoisChicagoUSA
  2. 2.Department of Electrical & Computer EngineeringUniversity of IllinoisChicagoUSA