This section provides resources for Geometric Deep Learning (GDL) and its applications in Computer-Aided Engineering (CAE). GDL applies deep learning techniques to non-Euclidean domains (such as graphs and manifolds) and is increasingly used to enhance simulation, design optimization, and analysis in engineering.
- Understanding Graph Neural Networks (GNNs)
- Core concepts in Geometric Deep Learning: theories, algorithms, and applications
- AMMI 2022 Course "Geometric Deep Learning"
- Graph Neural Networks" (Stanford CS224W)
- PyTorch Geometric Tutorials
- Deep Graph Library (DGL) Tutorials
- Geometric Deep Learning" by Michael Bronstein
- Geometric Deep Learning: Going beyond Euclidean data" by Bronstein et al.
- Geometric Deep Learning for Computer-Aided Design: A Survey" by Wu et al.
- Cadence's Generative AI Portfolio using Geometric Deep Learning
- Altair's physicsAI Application in CAE
- Engineering Intelligence with Neural Concept Shape
Geometric Deep Learning (GDL) is a core section for handling non-Euclidean CAE data. Michael Bronstein is a pioneer in this field, and his courses, lectures, and publications are essential for anyone wishing to dive deep into GDL. For those interested in practical experimentation, try replicating open-source implementations of models like PointNet or various graph neural networks available on platforms such as Papers with Code. Most implementations will utilize PyTorch Geometric, so familiarity with this library is highly recommended.
- Community Contributions:
You are encouraged to contribute additional resources, improvements, and feedback. Check out the initial repository at cae_ai_resources and submit a pull request with your suggestions.
Happy learning and contributing!