thi.ng is an open source collection of 20+ computational design tools for Clojure & Clojurescript: generative design, data visualization, digital fabrication, linked data, graph processing and more...
This is the Graph Neural Networks: Hands-on Session from the Stanford 2019 Fall CS224W course.
In this tutorial, we will explore the implementation of graph neural networks and investigate what representations these networks learn. Along the way, we'll see how PyTorch Geometric and TensorBoardX can help us with constructing and training graph models.
Pytorch Geometric tutorial part starts at -- 0:33:30
Details on:
* Graph Convolutional Neural Networks (GCN)
* Custom Convolutional Model
* Message passing
* Aggregation functions
* Update
* Graph Pooling
A pair of mathematicians has built on an obscure, 30-year-old mathematical theory to show that soap-filmlike minimal surfaces appear abundantly in a wide range