A learning algorithm for applying synthesized stable dynamics to system identification

James W. Howse, Chaouki T. Abdallah, Gregory L. Heileman

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


In this paper the models discussed by Cohen are extended by introducing an input term. This allows the resulting models to be utilized for system identification tasks. This approach gives a direct way to encode qualitative information such as attractor dimension into the model. We prove that this model is stable in the sense that a bounded input leads to a bounded state when a minor restriction is imposed on the Lyapunov function. By employing this stability result, we are able to find a learning algorithm which guarantees convergence to a set of parameters for which the error between the model trajectories and the desired trajectories vanishes.

Original languageEnglish (US)
Pages (from-to)81-87
Number of pages7
JournalNeural Networks
Issue number1
StatePublished - Jan 1998
Externally publishedYes


  • Learning algorithm
  • Stability
  • System identification

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence


Dive into the research topics of 'A learning algorithm for applying synthesized stable dynamics to system identification'. Together they form a unique fingerprint.

Cite this