News for hackers. Stuff that matters.
Re:Physics Forests by modeless on Monday November 16, 2015 @12:45AM (#10572827)
"Our approach showed the potential to be a good replacement of standard solvers in settings, where running times is more important than the exactness of a simulation, such as in computer games or interactive design."

"In our future work we want to [...] combine learning methods with standard solvers to obtain both fast and highly accurate simulations."

From the paper's conclusion.

There are no comments on this comment yet.