An experiment trying to extend Learning Mesh-Based Simulation with Graph Networks which remains competitive in mesh based simulation by making the model subequivariant.
Path tracing is an amazing algorithm for simulating light transport. While it's not physical in nature, it does simulate physical light well. In this series, we develop our intuition for and implement the path tracing algorithm.
Njoror aims to change the way we learn mathematics. It replaces the standardized boring lectures and heavy textbooks with interactive problems tailored specifically for the individual student following their own unique learning path.
We show that we are able to constrain the material composition of exoplanets given their mass and radius.
During a Datathon, we found evidence of misfitting in medical baseline models picking up text added to x-ray scan for classifying pathologies instead of the actual pathology location.
In recent years, neural networks have shown great potential across a wide range of industries. In this series, we look at how neural networks work from a theoretical point of view.
