If automatic integration were as easy as automatic differentiation, AI would be pretty close to solved
-
could you say more?
Presumably something like: you could automatically integrate the gradient and essentially skip the optimization of the cost function.
-
-
You can turn optimisation into the problem of computing the posterior distribution for the minimum (or minimiser, if you like), which is an integration problem
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.