Time series prediction by using a connectionist network with internal delay lines

@inproceedings{Wan1993TimeSP,
  title={Time series prediction by using a connectionist network with internal delay lines},
  author={E. A. Wan},
  year={1993}
}
A neural network architecture, which models synapses as Finite Impulse Response (FIR) linear lters, is discussed for use in time series prediction. Analysis and methodology are detailed in the context of the Santa Fe Institute Time Series Prediction Competition. Results of the competition show that the FIR network performed remarkably well on a chaotic laser intensity time series. 
Highly Influential
This paper has highly influenced 17 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 328 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 111 extracted citations

Recursive Bayesian Levenberg-Marquardt Training of Recurrent Neural Networks

2007 International Joint Conference on Neural Networks • 2007
View 6 Excerpts
Method Support
Highly Influenced

Improving the performance and accuracy of time series modeling based on autonomic computing systems

J. Ambient Intelligence and Humanized Computing • 2011
View 5 Excerpts
Highly Influenced

Time series prediction using artificial neural networks

Miguel Angel Pérez-Chavarría, Hugo Hidalgo-Silva, Francisco J. Ocampo-Torres
2009
View 14 Excerpts
Highly Influenced

Using time-dependent neural networks for EEG classification.

IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society • 2000
View 6 Excerpts
Method Support
Highly Influenced

328 Citations

01020'93'98'04'10'16
Citations per Year
Semantic Scholar estimates that this publication has 328 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 34 references

Bayesian Interpolation

D. MacKay
Neural Computations, • 1992
View 4 Excerpts
Highly Influenced

Practical Bayesian Framework for Backpropagation Networks

D. MacKay
in Neu- ral Computations, • 1992
View 4 Excerpts
Highly Influenced

Probabilistic displays

J. Skilling, D. Robinson, S. Gull
Maximum Entropy and Bayesian Methods, Laramie • 1990
View 3 Excerpts