There has been much discussion about the “black box” problem of neural networks. Sophisticated models can perform well on predictive workloads, but when it comes to backtracking how the system came to ...

Arriving at this graph neural network destination took the combined work of Google as well as Amazon, Waymo, and Sea AI Lab, but now provides Google Maps with a far more accurate ETA and the ability ...

BingoCGN, a scalable and efficient graph neural network accelerator that enables inference of real-time, large-scale graphs through graph partitioning, has been developed by researchers at ...

A team of chemistry, life science, and AI researchers are using graph neural networks to identify molecules and predict smells. Models made by researchers outperform current state-of-the-art ...