Sökning: "Graph Neural Networks"

Visar resultat 1 - 5 av 26 avhandlingar innehållade orden Graph Neural Networks.

  1. 1. Mathematical Foundations of Equivariant Neural Networks

    Författare :Jimmy Aronsson; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; symmetry; geometric deep learning; gauge theory; induced representations; fiber bundles; convolutional neural networks; equivariance;

    Sammanfattning : Deep learning has revolutionized industry and academic research. Over the past decade, neural networks have been used to solve a multitude of previously unsolved problems and to significantly improve the state of the art on other tasks. However, training a neural network typically requires large amounts of data and computational resources. LÄS MER

  3. 2. Enabling Enterprise Live Video Streaming with Reinforcement Learning and Graph Neural Networks

    Författare :Stefanos Antaris; Sarunas Girdzijauskas; Dimitrios Katsaros; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Graph Neural Networks; Reinforcement Learning; Meta-Learning; Knowledge Distillation; Enterprise Liveo Video Streaming;

    Sammanfattning : Over the last decade, video has vastly become the most popular way the world consumes content. Due to the increased popularity, video has been a strategic tool for enterprises. LÄS MER

  4. 3. Random geometric graphs and their applications in neuronal modelling

    Författare :Fioralba Ajazi; Matematisk statistik; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; random graph; Neural Network; Probability; Inhomogeneous random graph; random distance graph; random grown networks;

    Sammanfattning : Random graph theory is an important tool to study different problems arising from real world.In this thesis we study how to model connections between neurons (nodes) and synaptic connections (edges) in the brain using inhomogeneous random distance graph models. LÄS MER

  5. 4. Water–fat separation in magnetic resonance imaging and its application in studies of brown adipose tissue

    Författare :Jonathan Andersson; Joel Kullberg; Håkan Ahlström; Mark Lubberink; Kerstin Lagerstrand; Uppsala universitet; []
    Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; brown adipose tissue; magnetic resonance imaging; water–fat signal separation; graph-cut; positron emission tomography; 18F-fludeoxyglucose; infrared thermography; machine learning; artificial neural networks; deep learning; convolutional neural networks; Radiology; Radiologi;

    Sammanfattning : Virtually all the magnetic resonance imaging (MRI) signal of a human originates from water and fat molecules. By utilizing the property chemical shift the signal can be separated, creating water- and fat-only images. LÄS MER

  7. 5. On sparse voxel DAGs and memory efficient compression of surface attributes for real-time scenarios

    Författare :Dan Dolonius; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; directed acyclic graph; surface properties; neural networks; voxel; compression; spherical gaussians; light field; octree; filtering; geometry;

    Sammanfattning : The general shape of a 3D object can expeditiously be represented as, e.g., triangles or voxels, while smaller-scale features usually are parameterized over the surface of the object. LÄS MER