Variational Graph Auto-Encoder (VGAE)
Variational Graph Auto-Encoder (VGAE) was proposed by T. N. Kipf and M. Welling for link prediction, which is a key problem for network-structured data.
Da Vinci – A Scaleable Architecture for Neural Network Computing (updated v7)
In this presentation, we introduce microprocessor trends, describe two distinct eras of computing usage in training AI systems and show the wide variety of computing architectures.
Graph Convolutional Network (GCN)
Graph Neural Networks (GNNs) have gained immense popularity as a new methodology of analysing graphs, similar to how we use deep learning to process images.
Prediction of protein subcellular localization
Use deep learning tools to accurately identify the organelles where proteins are located in human protein fluorescence micrographs.
Retinal blood vessel segmentation in the eyeground
The fundus retinal blood vessel segmentation application was developed for the Atlas 200 DK inference system.