University of Hertfordshire

Input window size and neural network predictors

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

Documents

  • 900909

    Accepted author manuscript, 37 KB, PDF document

  • R. Frank
  • N. Davey
  • Stephen Hunt
View graph of relations
Original languageEnglish
Title of host publicationProcs of the IEEE-INNS-ENNS Int Joint Conf on Neural Networks, 2000 (IJCNN 2000)
PublisherIEEE
Pages237-242
Volume2
ISBN (Print) 0-7695-0619-4
DOIs
Publication statusPublished - 2000

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

ID: 422507