Differential Neural Network Identification ...
Document type :
Communication dans un congrès avec actes
Title :
Differential Neural Network Identification for Homogeneous Dynamical Systems ⋆
Author(s) :
Ballesteros, Mariana [Auteur]
Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional [CINVESTAV]
Polyakov, Andrey [Auteur]
Finite-time control and estimation for distributed systems [VALSE]
Efimov, Denis [Auteur]
Finite-time control and estimation for distributed systems [VALSE]
Chairez, Isaac [Auteur]
Instituto Politechnico National [IPN]
Poznyak, Alexander [Auteur]
Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional [CINVESTAV]
Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional [CINVESTAV]
Polyakov, Andrey [Auteur]
Finite-time control and estimation for distributed systems [VALSE]
Efimov, Denis [Auteur]
Finite-time control and estimation for distributed systems [VALSE]
Chairez, Isaac [Auteur]
Instituto Politechnico National [IPN]
Poznyak, Alexander [Auteur]
Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional [CINVESTAV]
Conference title :
NOLCOS 2019 - 11th IFAC Symposium on Nonlinear Control Systems
City :
Vienna
Country :
Autriche
Start date of the conference :
2019-09-04
English keyword(s) :
Differential Neural Network
Nonlinear Systems
Homogeneous systems
Identification
Nonlinear Systems
Homogeneous systems
Identification
HAL domain(s) :
Informatique [cs]/Automatique
English abstract : [en]
In this paper, a non parametric identifier for homogeneous nonlinear systems affine in the input is proposed. The identification algorithm is based on the neural networks using sigmoidal activation functions. The learning ...
Show more >In this paper, a non parametric identifier for homogeneous nonlinear systems affine in the input is proposed. The identification algorithm is based on the neural networks using sigmoidal activation functions. The learning algorithm is derived by means of Lyapunov function method and homogeneity theory. A numerical example demonstrates the performance of the proposed identifier.Show less >
Show more >In this paper, a non parametric identifier for homogeneous nonlinear systems affine in the input is proposed. The identification algorithm is based on the neural networks using sigmoidal activation functions. The learning algorithm is derived by means of Lyapunov function method and homogeneity theory. A numerical example demonstrates the performance of the proposed identifier.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-02278726/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02278726/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02278726/document
- Open access
- Access the document
- document
- Open access
- Access the document
- FINAL.pdf
- Open access
- Access the document