Graph Convolutional Neural Networks

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?"

Publisher

Software Engineering Institute

Watch

Abstract

This project used graph signal processing formalisms to create new deep learning tools for graph convolutional neural networks (GCNNs). Our approach employed topology-adaptive graph convolutional networks, introduced in 2017 by researchers at Carnegie Mellon University.

Software Engineering Institute