Data-reusing recurrent neural adaptive filters

Authors:
Danilo P. Mandic
Affiliations:
School of Information Systems, University of East Anglia, Norwich, NR4 7TJ, U.K.
Venue:
Neural Computation
Year:
2002

Citing 8
Cited 2

Theory and design of adaptive filters

Theory and design of adaptive filters
Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms

Neural Computation
Relating the slope of the activation function and the learning rate within a recurrent neural network

Neural Computation
A normalised real time recurrent learning algorithm

Signal Processing - Special issue on current topics in adaptive filtering for hands-free acoustic communication and beyond
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
State Variables for Engineers

State Variables for Engineers
Relationships Between the A Priori and A Posteriori Errors in Nonlinear Adaptive Neural Filters

Neural Computation

A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation

IEEE Transactions on Neural Networks
Novel stability analysis for recurrent neural networks with multiple delays via line integral-type L-K functional

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A class of data-reusing learning algorithms for real-time recurrent neural networks (RNNs) is analyzed. The analysis is undertaken for a general sigmoid nonlinear activation function of a neuron for the real time recurrent learning training algorithm. Error bounds and convergence conditions for such data-reusing algorithms are provided for both contractive and expansive activation functions. The analysis is undertaken for various configurations that are generalizations of a linear structure infinite impulse response adaptive filter.