I would bet against current backprop-based techniques in the long run.https://twitter.com/michael_nielsen/status/669978274701942785 …
-
@fchollet@michael_nielsen I can't see local (even global sometimes) optimization without doing gradient descent in *some * space.
@edersantana @michael_nielsen learning problems can be formulated as numerical optimization problems, but that is not the only way.
-
-
@fchollet@michael_nielsen ban genetic algorithms xD. can you elaborate or link to what you mean? -
@edersantana@michael_nielsen computing exact solutions (e.g. matrix factorization, matrix inversion) v.s. searching for num. approximation - Show replies
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.