October 2, 2018 – IEEE DAY CELEBRATION, 6-8pm, AT&T Labs
Topic: “Intro to Graph Convolutional Networks”
Graham Ganssle, Ph.D., P.G.
Head of Data Science, Expero
PLEASE RSVP – (is required to access the AT&T building)
Is this group of delis a money laundering ring, or are they simply exchanging provolone? Why does Devin have so many Facebook friends, and I only have a handful? The answer to one of these questions is obvious (because I’m a nerd giving an ML presentation), but both can be solved with graph convolutional networks. GCNs use a novel neural network kernelization which generalizes the accuracy and speed of CNNs to non-Euclidean information spaces. Join me for a chat about the applications of GCNs, the elegance of convolutional mathematics, and what the hell non-Euclidean means. I’ll even send you home with the party favor of GCN open source software.
Graham is a recovering physicist, deep learning his way through a world of digital signals. He is the head of data science at Expero Inc, where, with the synergy of his expert team, he uses data to explore the domains of finance, supply chain optimization, energy, and health care.
Come and join us with IEEE Celebration
For any details, please email F.Behmann@IEEE.org