Time series prediction via neural network inversion

Lian Yan, David J. Miller

    Research output: Contribution to journalConference articlepeer-review

    1 Scopus citations

    Abstract

    In this work, we propose neural network inversion of a backward predictor as a technique for multi-step prediction of dynamic time series. It may be difficult to train a large network to capture the correlation that exists in some dynamic time series represented by small data sets. The new approach combines an estimate obtained from a forward predictor with an estimate obtained by inverting a backward predictor to more efficiently capture the correlation and to achieve more accurate predictions. Inversion allows us to make causal use of prediction backward in time. Also a new regularization method is developed to make neural network inversion less ill-posed. Experimental results on two benchmark time series demonstrate the new approach's significant improvement over standard forward prediction, given comparable complexity.

    Original languageEnglish (US)
    Pages (from-to)1049-1052
    Number of pages4
    JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
    Volume2
    StatePublished - 1999
    EventProceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) - Phoenix, AZ, USA
    Duration: Mar 15 1999Mar 19 1999

    All Science Journal Classification (ASJC) codes

    • Software
    • Signal Processing
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Time series prediction via neural network inversion'. Together they form a unique fingerprint.

    Cite this