Introduction to Graph Neural Networks

Join triple Kaggle Grandmaster, Usha Rengaraju, to learn about the basic mechanism of graph neural networks and the concepts and methods in unsupervised node outlier detection on graphs. The graph neural network (GNN) has become a dominant and powerful tool in mining graph data and is designed to encode the graph structure and learn a node’s embedding.

Register now to learn about why GNN exists, how they are used in real-world applications, and the basic architecture of how it works.

About the speaker

Usha currently heads the data science research at Exa Protocol, and she is the World’s first women triple Kaggle Grandmaster. She specializes in Deep Learning and Probabilistic Graphical Models and was one of the TigerGraph “ Graph for all - Million Dollar Challenge” judges in 2022.

Usha ranked as one of the top ten Data Scientists in India for the year 2020 by Analytics India Magazine, as one of the top ten women data scientists by Analytics Insight magazine for 2021, and as one of the top 150 AI Leaders and Influencers by 3AI magazine. She organized NeuroAI, which is India’s first-ever research symposium on the interface of Neuroscience and Data Science. She also organized the Neurodiversity India Summit, which is India’s first-ever conference in Neurodiversity.

Usha is one of the winners of “ML in Action” competition organized by the ML Developer programs team at Google, and her team won first place in the WiDS 2022 datathon organized by Stanford University.