A Transputer Based Neural Network Development System for Industrial Control Applications

  • J. P. Ruiz-Miguela
  • P. J. Brunn


Once they have been configured, Neural Networks provide, often the only means of solving difficult control problems. However, the time and computing power required to set-up the network co-efficients can be prohibitive. This paper reviews a project to investigate the use of parallel processing, in particular transputers, to evaluate the parameters for Neural Networks. Three different algorithms are used to parallelise the learning process and their relative advantages are discussed. Back propagation by epoch with the training set distributed between the transputer is found to be most suitable for the types of control problems investigated


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. (FAHL87).
    Fahlman, SE and Hinton, GE ‘Connectionist Architects for Artificial Intelligence’ IEEE Computer, 20, pp100–109, 1987.CrossRefGoogle Scholar
  2. (INMO89).
    INMOS ‘The Transputer Databook’ 2nd Edition, Bristol, 1989.Google Scholar
  3. (RUIZ92).
    Ruiz-Miguela JP ‘A Transputer Based Neural Network Development System’ MSc Dissertation UMIST 1992Google Scholar
  4. (RUME86).
    Rumelhart DE & McClelland JL and the PDP Research Group. ‘Parallel Distributed Processing: Explorations in the Microstructure of Cognition Vol. I: Foundations’ MIT Press Cambridge MA, 1986.Google Scholar
  5. (3L89).
    3L Ltd ‘Parallel Pascal User Guide’ 1989.Google Scholar

Copyright information

© Department of Mechanical Engineering University of Manchester Institute of Science and Technology 1993

Authors and Affiliations

  • J. P. Ruiz-Miguela
    • 1
  • P. J. Brunn
    • 1
  1. 1.UMISTUK

Personalised recommendations