Dynamic subgrouping in RTRL provides a faster O(N/sup 2/) algorithm

Authors:
N. R. Euliano;J. C. Principe
Affiliations:
Comput. Neuro Eng. Lab., Florida Univ., Gainesville, FL, USA;-
Venue:
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 06
Year:
2000

Citing 0
Cited 2

Principles and networks for self-organization in space-time

Neural Networks - New developments in self-organizing maps
Letters: Efficient online recurrent connectionist learning with the ensemble Kalman filter

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Static grouping of processing elements (PEs) has been proposed to reduce the computational complexity of real time recurrent learning (RTRL) from O(n/sup 4/) to O(n/sup 2/), but performance suffers. This paper proposes a dynamic subgrouping of PEs estimated from a local approximation of the /spl pi/ matrix based on temporal Hebbian of sensitivities during training. The method is O(n/sup 2/) and leads to better performance.