Three problems associated with uncertainty in feedforward neural network predictions are discussed. First, the uncertainty present in the input vector propagates through a trained network into the output vector, and this uncer- tainty is determined using the matrix of partial derivatives defining the change in each output with respect to the inputs. Second, because the partial derivative information conveys the relative sensitivity of a given output to each of the inputs, it can be used as a tool to determine the relevance of each of the inputs to the out prediction. Finally, the influence of random choices for training and testing data sets is investigated. The variability in these solutions provides a measure of the fossilized bias error in the network with respect to development decisions. The approaches are illustrated using examples of four-quadrant propeller predictions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Uncertainty Analysis Applied to Feedforward Neural Networks



    Published in:

    Ship Technology Research ; 54 , 3 ; 114-124


    Publication date :

    2007-07-01


    Size :

    11 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Adaptive Type Feedforward Feedback Controller Using Neural Networks

    Yamada, T. / Yabuta, T. | British Library Online Contents | 1994


    Efficient supervised learning of multilayer feedforward neural networks

    Osowski, S. / Stodolski, M. / Bojarczak, P. | IEEE | 1994


    Efficient Supervised Learning of Multilayer Feedforward Neural Networks

    Osowski, S. / Stodolski, M. / Bojarczak, P. et al. | British Library Conference Proceedings | 1994


    Feedforward Control under the Presence of Uncertainty

    Faanes, A. / Skogestad, S. | British Library Online Contents | 2004