A powerful machine learning algorithm should be able to dynamically tune both its own model parameters and hyper parameters.
-
nah, tweaking the "evolution process" means changing network architecture, or even the iterative design process.
hyperparameters all the way up. At some point you'll have to tweak the fundamental physical constants of your universe
-
-
ok I think I get your point, but I wouldn't say the difference between recurrent and feed fwd is a hyperparameter.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
lol, why constrain ourselves to reality?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.