A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction

@article{Chen1999ARL,
  title={A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction},
  author={C. L. Philip Chen and J. Z. Wan},
  journal={IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society},
  year={1999},
  volume={29 1},
  pages={62-72}
}
A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the flat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating… CONTINUE READING
Highly Cited
This paper has 121 citations. REVIEW CITATIONS
51 Citations
0 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 51 extracted citations

122 Citations

0102030'99'03'08'13'18
Citations per Year
Semantic Scholar estimates that this publication has 122 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…