Differential Neural Network Identification for Homogeneous Dynamical Systems ⋆

Mariana Ballesteros (1) , Andrey Polyakov (2) , Denis Efimov (2) , Isaac Chairez (3) , Alexander Poznyak (1)

1 CINVESTAV - Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional
2 VALSE - Finite-time control and estimation for distributed systems
3 IPN - Instituto Politechnico National

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.

Mots clés: Differential Neural Network; Nonlinear Systems; Homogeneous systems; Identification

Domaines: Automatique

Mariana Ballesteros, Andrey Polyakov, Denis Efimov, Isaac Chairez, Alexander Poznyak. Differential Neural Network Identification for Homogeneous Dynamical Systems ⋆. NOLCOS 2019 - 11th IFAC Symposium on Nonlinear Control Systems, Sep 2019, Vienna, Austria. ⟨hal-02278726⟩