\(\mathcal L_{2}-\mathcal L_{\infty }\) nonlinear system identification via recurrent neural networks

DOI10.1007/S11071-010-9741-3zbMath1209.93035OpenAlexW2094731610MaRDI QIDQ2431028

Choon Ki Ahn

Publication date: 8 April 2011

Published in: Nonlinear Dynamics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11071-010-9741-3

zbMATH Keywords

recurrent neural networkslinear matrix inequality (LMI)input-to-state stability (ISS)weight learning law\(\mathcal L_{2}-\mathcal L_{\infty }\) identification

Mathematics Subject Classification ID

System identification (93B30) (H^infty)-control (93B36)

Related Items (3)

Peak-to-peak exponential direct learning of continuous-time recurrent neural network models: a matrix inequality approach ⋮ Sets of generalized \(\mathcal H_2\) exponential stability criteria for switched multilayer dynamic neural networks ⋮ Input-to-state stability for dynamical neural networks with time-varying delays

Uses Software

• LMI toolbox

Cites Work

• Unnamed Item
• On characterizations of the input-to-state stability property
• Identification of nonlinear dynamical systems using multilayered neural networks
• Adaptive control of chaos in Lorenz system
• Stability of adaptive controllers
• Neural networks for control systems - a survey
• Optimal unbiased filtering via linear matrix inequalities
• Robust filtering with guaranteed energy-to-peak performance -- \({\mathcal LMI}\) approach
• Robust training algorithm of multilayered neural networks for identification of nonlinear dynamic systems
• Delay-dependent robust H/sub ∞/ and L/sub 2/-L/sub ∞/ filtering for a class of uncertain nonlinear time-delay systems
• Robust L/sub 2/-L∞ filtering for uncertain systems with multiple time-varying state delays
• Neurons with graded response have collective computational properties like those of two-state neurons.

This page was built for publication: \(\mathcal L_{2}-\mathcal L_{\infty }\) nonlinear system identification via recurrent neural networks