Realization theory of recurrent neural ODEs using polynomial system embeddings

DOI10.1016/j.sysconle.2023.105468zbMath1519.93049arXiv2205.11989OpenAlexW4319066081MaRDI QIDQ6160839

Mihaly Petreczky, Hatem Hajri, Thibault Defourneau, Martin Gonzalez

Publication date: 26 June 2023

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2205.11989

zbMATH Keywords

system identificationrecurrent neural networksrealization theorylong short-term memoryneural ODEs

Mathematics Subject Classification ID

System identification (93B30) Observability (93B07) Attainable sets, reachability (93B03) Realizations from input-output data (93B15) Control/observation systems governed by ordinary differential equations (93C15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Realization theory for rational systems: minimal rational realizations
• Nonlinear control systems: An introduction
• Rational systems and observation fields
• Minimal polynomial realizations
• Further results on controllability of recurrent neural networks
• State observability in recurrent neural networks
• Realization Theory of Nash Systems
• Realization Theory for Rational Systems: The Existence of Rational Realizations
• Algebraic Differential Equations and Rational Control Systems
• Nonlinear controllability and observability
• Linear Stochastic Systems
• Mathematical Description of Linear Dynamical Systems

This page was built for publication: Realization theory of recurrent neural ODEs using polynomial system embeddings