Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks.
Shih-Hsin WangYung-Chang HsuJustin M. BakerAndrea L. BertozziJack XinBao WangPublished in: ICLR (2024)
Keyphrases
- neural network
- feature space
- genetic algorithm
- graph structure
- fuzzy logic
- artificial neural networks
- feature vectors
- prior knowledge
- classification accuracy
- pattern recognition
- feature set
- back propagation
- false positives
- self organizing maps
- structural information
- recurrent neural networks
- video sequences
- graph mining
- extracted features