Properties of neural networks with applications to modelling non-linear dynamical systems

1992/01/01 by S. A. BILLINGS, S.A. Billings, H. B. JAMALUDDIN +3 · 246 citations
Computer Science · Engineering · Mathematics · #Artificial intelligence #Artificial neural network #Computer science #Control (management) #Control Systems and Identification #Control theory (sociology) #Dynamical systems theory #Engineering #Fault Detection and Control Systems #Linear dynamical system #Linear system #Mathematics #Neural Networks and Applications #Node (physics) #Noise (video) #Physics #Selection (genetic algorithm) #Stochastic neural network #Time delay neural network

paper · pdf · doi:10.1080/00207179208934232

published in International Journal of Control 55(1), 193-224 (Taylor & Francis)

openalex publication_date 1992/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Properties of neural network performance are investigated by studying the modelling of non-linear dynamical systems. Network complexity, node selection, prediction and the effects of noise are studied and some new metrics of performance are introduced. The results are illustrated with both simulated and industrial examples.

Cited by

• Forgery Cyber-Attack Supported by LSTM Neural Network: An Experimental Case Study. [europepmc]

Related

• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• Identification and control of dynamical systems using neural networks
• A Novel Neural Filter to Improve Accuracy of Neural Network Models of Dynamic Systems
• Constructing Neural Network-Based Models for Simulating Dynamical Systems
• Physics guided neural networks for modelling of non-linear dynamics