Journal Article10.1016/J.NEUCOM.2006.09.004
Nonlinear system identification with recurrent neural networks and dead-zone Kalman filter algorithm
José de Jesús Rubio,Wen Yu +1 more
119
TL;DR: Extended Kalman filter is applied to train state-space recurrent neural networks for nonlinear system identification and Lyapunov method is used to prove that theKalman filter training is stable.
read more
About: This article is published in Neurocomputing. The article was published on 01 Aug 2007. The article focuses on the topics: Extended Kalman filter & Fast Kalman filter.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Self-Evolving Interval Type-2 Fuzzy Neural Network With Online Structure and Parameter Learning
Chia-Feng Juang,Yu-Wei Tsao +1 more
TL;DR: This paper proposes a self-evolving interval type-2 fuzzy neural network (SEIT2FNN) with online structure and parameter learning, which is applied to simulations on nonlinear plant modeling, adaptive noise cancellation, and chaotic signal prediction.
315
A novel memristive neural network with hidden attractors and its circuitry implementation
TL;DR: Interestingly, the memristive neural network can generate hyperchaotic attractors without the presence of equilibrium points and circuital implementation of such memristives is presented to show its feasibility.
204
A recurrent self-evolving fuzzy neural network with local feedbacks and its application to dynamic system processing
TL;DR: The proposed recurrent self-evolving fuzzy neural network with local feedbacks (RSEFNN-LF) is applied to dynamic system identification, chaotic sequence prediction, and speech recognition problems and is compared with other recurrent fuzzy neural networks.
112
Uniformly Stable Backpropagation Algorithm to Train a Feedforward Neural Network
TL;DR: A theorem is stated and proven which guarantees uniform stability of a general discrete-time system and the backpropagation (BP) algorithm with a new time-varying rate is uniformly stable for online identification and the identification error converges to a small zone bounded by the uncertainty.
Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay
TL;DR: Based on the proposed passive learning law, some new stability results, such as asymptotical stability, input-to-state stability (ISS), and bounded input-bounded output (BIBO) stability, are presented.
90
References
•Book
Neural Networks: A Comprehensive Foundation
Simon Haykin
- 16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
High-order neural network structures for identification of dynamical systems
TL;DR: This paper studies the approximation and learning properties of one class of recurrent networks, known as high-order neural networks; and applies these architectures to the identification of dynamical systems.
838
Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks
G.V. Puskorius,L.A. Feldkamp +1 more
TL;DR: These simulations suggest that recurrent controller networks trained by Kalman filter methods can combine the traditional features of state-space controllers and observers in a homogeneous architecture for nonlinear dynamical systems, while simultaneously exhibiting less sensitivity than do purely feedforward controller networks to changes in plant parameters and measurement noise.
614