This paper proposed the single input multiple outputs (SIMO) Fourier neural networks on the base of Fourier series principle. The SIMO Fourier neural networks turn nonlinear optimization problem into linear optimization problem. So, the SIMO Fourier neural networks highly improve convergence speed and avoid local minima problem. At the same time, under the condition of bounded input and bounded output, the SIMO Fourier neural networks can approximate multiple arbitrary nonlinear mapping relationship at arbitrary accuracy and have good generalization capability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    SIMO Fourier neural networks research


    Contributors:
    Xuhua Yang, (author) / Huaping Dai, (author) / Youxian Sun, (author)


    Publication date :

    2003-01-01


    Size :

    249443 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    SIMO Fourier Neural Networks Research

    Yang, X. / Dai, H. / Sun, Y. et al. | British Library Conference Proceedings | 2003


    Research on SIMO Fourier Neural Networks Based on Least Square Method

    Yang, X.-h. / Dai, H.-p. / Sun, Y.-x. | British Library Online Contents | 2004



    On Transfer Learning for a Fully Convolutional Deep Neural SIMO Receiver

    Uyoata, Uyoata E. / Adeogun, Ramoni O. | IEEE | 2024