Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings - IRT SystemX Accéder directement au contenu
Article Dans Une Revue Systems & Control Letters Année : 2023

Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings

Résumé

In this paper we show that neural ODE analogs of recurrent (ODE-RNN) and Long Short-Term Memory (ODE-LSTM) networks can be algorithmically embedded into the class of polynomial systems. This embedding preserves input-output behavior and can suitably be extended to other neural DE architectures. We then use realization theory of polynomial systems to provide necessary conditions for an input-output map to be realizable by an ODE-LSTM and sufficient conditions for minimality of such systems. These results represent the first steps towards realization theory of recurrent neural ODE architectures, which is is expected be useful for model reduction and learning algorithm analysis of recurrent neural ODEs.
Fichier principal
Vignette du fichier
2205.11989.pdf (194.53 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
licence : CC BY - Paternité

Dates et versions

hal-03872484 , version 1 (25-11-2022)

Identifiants

Citer

Martin Gonzalez, Thibault Defourneau, Hatem Hajri, Petreczky Mihaly. Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings. Systems & Control Letters, 2023, 173, pp.105468. ⟨hal-03872484⟩
103 Consultations
32 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More