Re:Facebook has a neural network that can do advanced math
by savanaly on Tuesday December 17, 2019 @08:00PM
(#21820779)
Un-differentiable output. Take, for instance, writing a program. Change the input by the smallest possible amount, one character, and generally the output changes by a rather large amount (it could, say, go from working to failing to compile). Rarely would changing one character get us X% closer to a solution, or produce a change in a working solution that is X% faster.
[ Parent
| on HN ]
Re:Facebook has a neural network that can do advanced math
by mturmon on Tuesday December 17, 2019 @08:35PM
(#21820955)
OTOH, the example in the OP has somewhat the flavor of the hard problem you just sketched.
The tree-based (RPN-esque) notation itself gets around much of the "perturbed program fails to compile" problem.