Sökning: "Simple Graph Convolution"

Hittade 2 uppsatser innehållade orden Simple Graph Convolution.

  1. 1. Multimodal Machine Learning in Human Motion Analysis

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Jia Fu; [2022]
    Nyckelord :Multimodal machine learning; Modal fusion; Human motion classification; Multimodal maskininlärning; Modal fusion; Mänsklig rörelseklassificering;

    Sammanfattning : Currently, most long-term human motion classification and prediction tasks are driven by spatio-temporal data of the human trunk. In addition, data with multiple modalities can change idiosyncratically with human motion, such as electromyography (EMG) of specific muscles and respiratory rhythm. LÄS MER

  3. 2. Graph Neural Networks for Article Recommendation based on Implicit User Feedback and Content

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Márk Bereczki; [2021]
    Nyckelord :Recommender systems; Implicit recommendation; Graph neural networks; Simple Graph Convolution; Natural language processing; Rekommendationssystem; Implicit rekommendation; Grafneurala nätverk; Simple Graph Convolution; Naturlig språkbehandling;

    Sammanfattning : Recommender systems are widely used in websites and applications to help users find relevant content based on their interests. Graph neural networks achieved state- of-the- art results in the field of recommender systems, working on data represented in the form of a graph. LÄS MER