Efficient, Interpretable Atomistic Graph Neural Network Representation for Angle-dependent Properties and its Application to Optical Spectroscopy Prediction.
Tim HsuNathan KeilbartStephen WeitznerJames ChapmanPenghao XiaoTuan Anh PhamS. Roger QiuXiao ChenBrandon C. WoodPublished in: CoRR (2021)
Keyphrases
- neural network
- prediction model
- graph representation
- artificial neural networks
- prediction accuracy
- pattern recognition
- graphical representation
- graph theory
- graph structure
- spanning tree
- neural network ensemble
- self organizing maps
- classification rules
- multilayer perceptron
- infrared
- multi layer perceptron
- back propagation
- relative position
- graph theoretic
- fuzzy logic
- graph structures