The Federal Aviation Administration is funding research into how neural networks, a form of artificial intelligence, might someday improve collision avoidance logic. These computational models mimic the layers of neurons in the human brain. The artificial versions are not nearly as complex as the brain, but they learn to solve problems efficiently through repeated exposure to data.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Solving the trust issue for neural nets


    Published in:

    Publication date :

    2017



    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English



    Classification :

    Local classification TIB:    770/7040
    BKL:    55.88 Luftverkehr, Raumfahrt / 55.88



    Neural Network Development Tool (NETS)

    Baffes, Paul T. | NTRS | 1990


    Efficiently Solving the Fractional Trust Region Problem

    Eriksson, Anders P. / Olsson, Carl / Kahl, Fredrik | Springer Verlag | 2007


    Solving the Infeasible Trust-Region Problem Using Approximations

    Perez, Victor / Eldred, Michael / Renaud, John | AIAA | 2004



    Extending classical pipeline models with neural nets

    Geiger, Gerhard / Matko, Drago / Werner, Thomas | Tema Archive | 2003