Recurrent neural networks training with stable bounding ellipsoid algorithm

Authors:
Wen Yu;José De Jesús Rubio
Affiliations:
Departamento de Control Automático, CINVESTAV-IPN, México, México;Sección de Estudios de Posgrado e Investigación, Instituto Politécnico Nacional-ESIME Azcapotzalco, México, México
Venue:
IEEE Transactions on Neural Networks
Year:
2009

Citing 12
Cited 4

Training multilayer perceptrons with the extended Kalman algorithm

Advances in neural information processing systems 1
Comparative Analysis of Backpropagation and the Extended Kalman Filter for Training Multilayer Perceptrons

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Informatics and computer science intelligent systems applications
Nonlinear system identification with recurrent neural networks and dead-zone Kalman filter algorithm

Neurocomputing
Robust minimum variance beamforming

IEEE Transactions on Signal Processing
Multiweight optimization in optimal bounding ellipsoid algorithms

IEEE Transactions on Signal Processing
Fuzzy function approximation with ellipsoidal rules

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An ellipsoidal calculus based on propagation and fusion

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Input-to-state stability for discrete-time nonlinear systems

Automatica (Journal of IFAC)
An algorithmic approach to adaptive state filtering using recurrent neural networks

IEEE Transactions on Neural Networks
High-order neural network structures for identification of dynamical systems

IEEE Transactions on Neural Networks

Takagi---Sugeno Fuzzy Hopfield Neural Networks for $${\mathcal{H}_{\infty}}$$ Nonlinear System Identification

Neural Processing Letters
Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks

Neurocomputing
Evolving intelligent algorithms for the modelling of brain and eye signals

Applied Soft Computing
Evolving intelligent system for the modelling of nonlinear systems with dead-zone input

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bounding ellipsoid (BE) algorithms offer an attractive alternative to traditional training algorithms for neural networks, for example, backpropagation and least squares methods. The benefits include high computational efficiency and fast convergence speed. In this paper, we propose an ellipsoid propagation algorithm to train the weights of recurrent neural networks for nonlinear systems identification. Both hidden layers and output layers can be updated. The stability of the BE algorithm is proven.