[SpaceBar]

If you expose a neural network to enough empirical molecular orbitals, it’s going to notice ‘patterns’ that are better than using say the radial solution of hydrogen (a gaussian). Picking chinese faces out of a crowd of billions is actually trickier.

[ModelBreaker]

“If you expose a neural network to enough empirical molecular orbitals, . . . “

But how do you get the data? Measurement is a problem.

[TigerLikesRoosterNew]

Scientists are running out of problems they can solve by hand or software like Matlab. They face problems which are too complex to deal with. There are astronomical number of cases to process in order to find a solution.

In a way, this is inevitable.