Nonlinear time series prediction with a discrete-time recurrent neural network model

N. Z. Hakim, J. J. Kaufman, G. Cerf, H. E. Meadows

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Summary form only given. The application of a discrete-time recurrent neural network model to signal processing and time series prediction was discussed. This network constitutes a black box model for input-output nonlinear system identification. Two samples were considered, which consisted of predicting a deterministic time series generated by the Mackey-Glass equation and a stochastic non-Gaussian time series. In the deterministic case, a 9-neuron network converged to a solution with prediction error comparable to that of feedforward networks, with faster learning than backpropagation, and absolutely no windowing or prior knowledge about the time series. In the stochastic case, a 25-neuron network was trained and converged to a solution close to the conditional mean (the optimal solution) also with no prior information or ad hoc assumptions. Ongoing research on the relation of neural networks to the Volterra-Wiener theory of nonlinear systems was also discussed.

Original languageEnglish
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages900
Number of pages1
ISBN (Print)0780301641
StatePublished - 1992
Externally publishedYes
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: 8 Jul 199112 Jul 1991

Publication series

NameProceedings. IJCNN - International Joint Conference on Neural Networks

Conference

ConferenceInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period8/07/9112/07/91

Fingerprint

Dive into the research topics of 'Nonlinear time series prediction with a discrete-time recurrent neural network model'. Together they form a unique fingerprint.

Cite this