High-dimensional and high-complexity unsupervised abnormal data recognition with neural networks remains an open research question. We propose a multi-level Variational Auto Encoder (VAE) structure in this work. First, based on traditional VAE, we deconstruct the original data using convolution kernels of different specifications to establish multiple feature latent spaces, thereby reducing the excessive data aggregation in the latent space. Then we use an equal-window convolution kernel to fuse feature blocks of different sizes, thereby transforming local features into globally identifiable features. Moreover, the model structure shortens the distance between the sub-feature block and the output end-point, reducing the training inefficiency caused by the vanishing gradient.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-level Variational Auto Encoder for Unsupervised Abnormal Data Recognition


    Beteiligte:
    Guan, Yaonan (Autor:in) / Yu, Yaru (Autor:in) / Wang, Gang (Autor:in) / Li, Dewei (Autor:in)


    Erscheinungsdatum :

    27.06.2022


    Format / Umfang :

    1246690 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Variational auto encoder for mixed data types

    Europäisches Patentamt | 2020

    Freier Zugriff

    AVAE: Adversarial Variational Auto Encoder

    Plumerault, Antoine / Borgne, Hervé Le / Hudelot, Céline | ArXiv | 2020

    Freier Zugriff

    Disentangled Variational Auto-Encoder for Semi-supervised Learning

    Li, Yang / Pan, Quan / Wang, Suhang et al. | ArXiv | 2017

    Freier Zugriff

    Disentangling Latent Factors of Variational Auto-Encoder with Whitening

    Hahn, Sangchul / Choi, Heeyoul | ArXiv | 2018

    Freier Zugriff