The author has developed an effective method for modelling very complex systems, called n-port symbolic neural (NPSN) modeling. Both production-rule sets and back-propagation multilayer neural nets are used as building blocks. This method is effective for the development of 'trained' models of real physical systems both for simulation of the system as built (with possible faults), and for the modeling of human control behavior. Methods have been devised to speed up the notoriously slow learning process in back-propagation networks. It is shown that if large networks are broken down into architectures of smaller networks to make the input-output data of each subnetwork strictly monotonic, this speeds up the training process. An NPSN model is being created to model the pilot in controlling an airplane in instrument-flying situations. The nature of NPSN models is described, and an example NPSN design cycle is considered.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Fast learning in symbolic/neural models using external constraints and automatic re-structuring


    Additional title:

    Schnelles Lernen in symbolisch/neuronalen Modellen mit externen Einschränkungen und automatischer Neustrukturierung


    Contributors:


    Publication date :

    1989


    Size :

    4 Seiten, 5 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    FIST: Fast Iterative Self-Structuring and Training of Artificial Neural Networks

    Garvin, A. D. M. / Rayner, P. J. W. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994


    Structuring neural network driver model

    Chikamori,S. / Kobayashi,M. / Shimizu,Y. et al. | Automotive engineering | 2000


    Multiple structuring element neural learning via cellular logic [2321-193]

    Shao, L. / Liu, L. / Li, G. et al. | British Library Conference Proceedings | 1994



    Symbolic road marking recognition using convolutional neural networks

    Ahmad, Touqeer / Ilstrup, David / Emami, Ebrahim et al. | IEEE | 2017