Mc Ghee is outrunned, NNs compute today 100 millions times faster than ODE methods !!!
This paper seems quite interesting but I spent unsuccessfully two hours trying to understand it. But nice cows indeed !A loss surface of a neural network can approximate anything. Including cows.
@Cuchullain, it seems that you put your finger exactly where it hurts ...It starts to sound like a married couple's argument. I'm outta here.