Time series prediction via neural network inversion

Lian Yan, David J. Miller

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


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
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


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

Cite this