Input window size and neural network predictors

R. Frank, N. Davey, Stephen Hunt

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    13 Citations (Scopus)
    47 Downloads (Pure)

    Abstract

    Neural network approaches to time series prediction are briefly discussed, and the need to specify an appropriately sized input window identified. Relevant theoretical results from dynamic systems theory are briefly introduced, and heuristics for finding the correct embedding dimension, and hence window size, are discussed. The method is applied to two time series and the resulting generalisation performance of the trained feedforward neural network predictors is analysed. It is shown that the heuristics can provide useful information in defining the appropriate network architecture
    Original languageEnglish
    Title of host publicationProcs of the IEEE-INNS-ENNS Int Joint Conf on Neural Networks, 2000 (IJCNN 2000)
    PublisherInstitute of Electrical and Electronics Engineers (IEEE)
    Pages237-242
    Volume2
    ISBN (Print) 0-7695-0619-4
    DOIs
    Publication statusPublished - 2000

    Fingerprint

    Dive into the research topics of 'Input window size and neural network predictors'. Together they form a unique fingerprint.

    Cite this