Completed
- Applying Convolution in Graphs
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Graph Neural Networks Implementation in Python
Automatically move to the next video in the Classroom when playback concludes
- 1 - Video Starts
- 2 - Video Introduction
- 3 - Tutorial Content in Part2
- 4 - Graph Representations Techniques
- 5 - Adjacency Matrix
- 6 - Incidence Matrix
- 7 - Degree Matrix
- 8 - Laplacian Matrix
- 9 - Creating Graph with NetworkX Jupyter notebook
- 10 - Graph Visualization with Node classes Jupyter notebook
- 11 - Graph Visualization with Node and Edge Labels Jupyter notebook
- 12 - Nodes Adjacency List Jupyter notebook
- 13 - Bag of Nodes
- 14 - Graph Walking Jupyter notebook
- 15 - GNN Concepts
- 16 - Role of Laplacian Matrix
- 17 - Convolution in Images
- 18 - Graph vs 2D fixed data types i.e. images, text
- 19 - Convolution on Graphs, how?
- 20 - Graph Feature Matrix
- 21 - Applying Convolution in Graphs
- 22 - Node Embeddings
- 23 - Message Passing in GNN
- 24 - Advantages of Node Embeddings
- 25 - GNN Use Cases
- 26 - Handling data in PyG Jupyter notebook
- 27 - GNN Experiment for Node grouping Jupyter notebook
- 28 - Node assignment to proper class Jupyter notebook
- 29 - GNN Model visualization with Netron
- 30 - Node classification using GNN in PyG
- 31 - Graph tSNE Visualization
- 32 - GNN Explainer
- 33 - Recap
