In automatic target recognition we often face a problem in having to train a large neural network upon a very limited data set. This paper presents methods designed to analyze trained networks. The methods allow us to investigate how the network makes its decisions as well as its generalization properties. The methods interact with each other and are intended to be used as a complete set. They use techniques of sensitivity analysis, linear algebra, and rule extraction. They have been coded in Matlab as a toolbox and tested on a large number of real networks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evaluation of neural networks for automatic target recognition


    Contributors:

    Published in:

    Publication date :

    1997-01-01


    Size :

    1249931 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluation of Neural Networks for Automatic Target Recognition

    Wojtek Przytula, K. / Thompson, D. / IEEE; Aerospace and Electronics Systems Society | British Library Conference Proceedings | 1997


    Neural networks for automatic target recognition

    Chaudhuri, S.P. / Sequeira, C. | Tema Archive | 1990


    Automatic target recognition for naval traffic control using neural networks

    Pasquariello, G. / Satalino, G. / La Forgia, V. et al. | British Library Online Contents | 1998



    Automatic target recognition using neural networks (invited Paper) [3466-37]

    Wang, L.-C. / Der, S. Z. / Nasrabadi, N. M. et al. | British Library Conference Proceedings | 1998