Using Machine Learning to Accelerate the Performance of Simulations

In physics, like, we don't believe that there's anything wrong with the differential equations that describe the physical systems. The way that you use the differential equations to actually simulate something just requires a lot of trade off. And i think the thing that we're seeing right now is there are some really powerful tools coming on line help with that problem. Itstad: You see things where your improvements come by orders of magnitude and huge new things become possible.