On realizability of neural networks-based input--output models in the classical state-space form

DOI10.1016/J.AUTOMATICA.2006.03.003MaRDI QIDQ856548zbMATH OpenOpenAlexFDO

Authors Ülle Kotta, F. Chowdhury, Sven Nõmm

Publication date 7 December 2006

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2006.03.003

zbMATH Keywords

neural networksrealizabilitydiscrete-time nonlinear systemsinput--output models

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Stochastic systems in control theory (general) (93E03)

Recommendations

• On realizability on neural networks-based input-output models
• Classical state space realizability of input-output bilinear models
• Two Approaches for State Space Realization of NARMA Models: Bridging the Gap
• Neural networks, rational functions, and realization theory
• Recursive identification using feedforward neural networks

Cites work

• Forward accessibility for recurrent neural networks
• Linearization of Discrete-Time Systems
• Predictive control based on neural network models with I/O feedback linearization
• State observability in recurrent neural networks
• Transfer equivalence and realization of nonlinear higher order input-output difference equations
• Two Approaches for State Space Realization of NARMA Models: Bridging the Gap

Cited in

(3)

• On realizability on neural networks-based input-output models
• Input-output linearization of discrete-time systems by dynamic output feedback
• scientific article; zbMATH DE number 5841486 (Why is no real title available?)

Describes a project that uses

Uses Software

• NNSYSID

This page was built for publication: On realizability of neural networks-based input--output models in the classical state-space form

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q856548)