A learning result for continuous-time recurrent neural networks

Eduardo D. Sontag

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

The following learning problem is considered, for continuous-time recurrent neural networks having sigmoidal activation functions. Given a "black box" representing an unknown system, measurements of output derivatives are collected, for a set of randomly generated inputs, and a network is used to approximate the observed behavior. It is shown that the number of inputs needed for reliable generalization (the sample complexity of the learning problem) is upper bounded by an expression that grows polynomially with the dimension of the network and logarithmically with the number of output derivatives being matched.

Original languageEnglish (US)
Pages (from-to)151-158
Number of pages8
JournalSystems and Control Letters
Volume34
Issue number3
DOIs
StatePublished - Jun 18 1998

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • General Computer Science
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Keywords

  • Computational learning theory
  • Recurrent neural networks
  • System identification

Fingerprint

Dive into the research topics of 'A learning result for continuous-time recurrent neural networks'. Together they form a unique fingerprint.

Cite this