Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach [Lecture Notes]
Ljubiša Stanković, Danilo P. Mandic
Abstract
Graph convolutional neural networks (GCNNs) are becoming a model of choice for learning on irregular domains. However, due to the black-box nature of NNs, their underlying principles are rarely examined in depth.
Topics & Concepts
Computer scienceConvolutional neural networkGraphArtificial intelligenceBasis (linear algebra)Theoretical computer scienceMachine learningMathematicsGeometryAdvanced Graph Neural NetworksMultimodal Machine Learning ApplicationsGraph Theory and Algorithms