Orthogonal neural networks (ONNs) are some powerful types of the neural networks in the modeling of non-linearity. They are constructed by the usage of orthogonal functions sets. Piecewise continuous orthogonal functions (PCOFs) are some important classes of orthogonal functions. In this work, based on a set of hyperbolic PCOFs, we propose the hyperbolic ONNs to identify the nonlinear dynamic systems. We train the proposed neural models with the stochastic gradient descent learning algorithm. Then, we prove the stability of this algorithm. Simulation results show the efficiencies of proposed model.
Ahmadi, G. (2022). Stochastic gradient-based hyperbolic orthogonal neural networks for nonlinear dynamic systems identification. Journal of Mathematical Modeling, 10(3), 529-547. doi: 10.22124/jmm.2022.21572.1890
MLA
Ghasem Ahmadi. "Stochastic gradient-based hyperbolic orthogonal neural networks for nonlinear dynamic systems identification". Journal of Mathematical Modeling, 10, 3, 2022, 529-547. doi: 10.22124/jmm.2022.21572.1890
HARVARD
Ahmadi, G. (2022). 'Stochastic gradient-based hyperbolic orthogonal neural networks for nonlinear dynamic systems identification', Journal of Mathematical Modeling, 10(3), pp. 529-547. doi: 10.22124/jmm.2022.21572.1890
VANCOUVER
Ahmadi, G. Stochastic gradient-based hyperbolic orthogonal neural networks for nonlinear dynamic systems identification. Journal of Mathematical Modeling, 2022; 10(3): 529-547. doi: 10.22124/jmm.2022.21572.1890