Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Danilo P. Mandic (2002) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: