Prediction with recurrent networks

Author

Wulff, Niels Holger ; Hertz, John A.

Author_Institution

CONNECT, Niels Bohr Inst., Copenhagen, Denmark

fYear

1992

fDate

31 Aug-2 Sep 1992

Firstpage

464

Lastpage

473

Abstract

The authors study extrapolation of time series using recurrent neural networks. They use the real-time recurrent learning algorithm introduced by R. J. Williams and D. Zipser (1989), both in the original form for first order nets and in a form for second order nets. It is shown that both the first order and the second order nets are able to learn to simulate the Mackey-Glass series. The prediction quality of the results is comparable to that from feedforward nets

Keywords

extrapolation; recurrent neural nets; time series; first order nets; prediction quality; real-time recurrent learning algorithm; recurrent neural networks; second order nets; Chaos; Delay; Differential equations; Extrapolation; Feedforward systems; Fractals; Polynomials; Recurrent neural networks; Sampling methods; Time measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop

Conference_Location

Helsingoer

Print_ISBN

0-7803-0557-4

Type

conf

DOI

10.1109/NNSP.1992.253666

Filename

253666

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3416388