With the development of science and technology, especially information technology, image processing technology has become an indispensable and powerful tool in scientific research. Traditional image processing methods cannot meet the needs. Researchers began to explore new and more effective methods. Among them, neural network image processing is the most active direction. Compared with traditional algorithms, neural network algorithm has the advantages of strong parallel computing ability, strong nonlinear imaging ability and strong adaptability. With the in-depth study of neural network theory, people have fully realized the advantages of neural network technology in parallel computing ability, nonlinear mapping and adaptability. Different neural network models are widely used in the field of image processing. Neural network technology has also become a hot research topic.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Application of Antagonism Neural Network in Data Processing of Graph Calculation


    Beteiligte:
    Wang, Yue (Autor:in)

    Erscheinungsdatum :

    2022-11-09


    Anmerkungen:

    doi:10.18686/esta.v9i3.235
    Electronics Science Technology and Application; Vol 9, No 3(Published); 85-88 ; 2424-8460 ; 2251-2608



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Graph-Enabled Intelligent Vehicular Network Data Processing

    Zheng, Zhigao / Bashir, Ali Kashif | IEEE | 2022



    Multi-graph hierarchical road network characterization method based on graph neural network

    WANG JINGYUAN / MA JINGTIAN / LI CHAO | Europäisches Patentamt | 2023

    Freier Zugriff

    Metro Traffic Flow Prediction via Knowledge Graph and Spatiotemporal Graph Neural Network

    Shun Wang / Yimei Lv / Yuan Peng et al. | DOAJ | 2022

    Freier Zugriff

    Spatial-Temporal Aware Inductive Graph Neural Network for C-ITS Data Recovery

    Liang, Wei / Li, Yuhui / Xie, Kun et al. | IEEE | 2023