Graph Convolutional Neural Networks (GCNN) Collection
These publications describe the SEI’s applied graph signal processing techniques that create new tools for GCNNs.
Software Engineering Institute
Large, complex datasets (e.g., sensor data, web traffic) require new approaches to graph processing. The SEI applied graph signal processing techniques to create new tools for graph convolutional neural networks (GCNNs), extending deep learning to graph problems.
November 12, 2019 • Video
By Oren Wright
Watch SEI researcher Mr. Oren Wright discuss using graph signal processing formalisms to create new deep learning tools for graph convolutional neural networks (GCNNs) to answer the question "how does AI learn structure?"watch