ML Anthology

Data-Reusing Recurrent Neural Adaptive Filters

Danilo P. Mandic
NeCo 2002 pp. 2693-2707
doi:10.1162/089976602760408026 /neco/2002/mandic2002neco-datareusing/

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.

NeCo Semantic Scholar

Cite

Text

Mandic. "Data-Reusing Recurrent Neural Adaptive Filters." Neural Computation, 2002. doi:10.1162/089976602760408026

Markdown

[Mandic. "Data-Reusing Recurrent Neural Adaptive Filters." Neural Computation, 2002.](https://mlanthology.org/neco/2002/mandic2002neco-datareusing/) doi:10.1162/089976602760408026

BibTeX

@article{mandic2002neco-datareusing,
  title     = {{Data-Reusing Recurrent Neural Adaptive Filters}},
  author    = {Mandic, Danilo P.},
  journal   = {Neural Computation},
  year      = {2002},
  pages     = {2693-2707},
  doi       = {10.1162/089976602760408026},
  volume    = {14},
  url       = {https://mlanthology.org/neco/2002/mandic2002neco-datareusing/}
}