{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f9137370ca9a4c0bb91e2f660ee646cb\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f9137370ca9a4c0bb91e2f660ee646cb-9ad25a5afbe40d29.gif","duration":119.147,"title":"Graph Neural Networks Fundamentals and Message Passing","description":"This Loom introduces the fundamentals of Graph Neural Networks by starting with core graph concepts and building intuition before neural network implementation. It explains graphs as nodes and edges with examples like social networks, recommendation systems, and molecular structures, and demonstrates graph representations including adjacency matrices and COO format. The video then covers node features as per-node feature vectors and explains the message passing idea where node representations are updated using information from neighbors. It proceeds to implement graph convolutional networks, first with NumPy and then using PyTorch, and briefly connects the approach to real-world graph learning tasks like classification."}