• fr
  • en
  • ×

    Personnalisez votre visitePersonalize your visitPersonnalisez votre visite

    PaysCountryPays


    France
    France
    Suisse
    United Kingdom
    Deutschland
    Ireland
    International
    Français
    English
    Deutsch

    ProfilProfileProfil


    ParticulierPrivate investorInvestisseur privé
    Investisseur professionnelProfessional investorInvestisseur professionnel

    AvertissementDisclaimerAvertissement

    AccepterAcceptAccepter

    Wasserstein GAN synthesis for time series with complex temporal dynamics: frugal architectures and arbitrary sample-size generation


    23-06-2023

    Th. Beroud, P. Abry, Y. Malevergne, M. Senneret, G. Perrin, J. Macq

    Generating time series with rich temporal dynamics using Deep Neural Network remains a challenging issue, attracting much research efforts.

    Instead of inventing yet another overperforming architecture, the present work aims to show that, when classic Wasserstein Generative Adversarial Networks are used,  architectures can be modified to reduce the overall number of trainable parameters down to five orders of magnitude (from 10.000.000 to 1.000), without decrease in the synthesis quality. This work also explains that these architecture modifications present the side benefit of permitting to synthesize longer time series than those used for training, without requiring to retrain the Deep Neural Network.

    These outcomes are obtained by using artificial time series whose complexity can be tuned and controlled, with scalefree, bursty and non time reversible temporal dynamics.

    Synthesis quality is also assessed quantitatively by means of multiscale analyses.

    This work can thus be considered a contribution towards sustainable Artificial Intelligence.

    This paper was published in ICASSP 2023, 48th International Conference on Acoustics, Speech and Signal Processing.

    > Download the research article
    > Download presentation (slides)
    > Download presentation (video)