@fchollet predictive models is the way to go. Everything is temporal. Future can only be predicted by good inference of causes.
Increasingly convinced that generative models are the wrong way to attack the problem of cognition
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet interesting, care to elaborate? I find the models on http://probmods.org , etc to be a natural way of thinking about cognition -
@bmabey need to do some experimentation first, but there's a potential paper in there somewhere
End of conversation
New conversation -
-
-
@fchollet in nutshell, why it is the wrong approach? Papers? Blogs? Negative results?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet any reason why ? They are very useful especially if you have lots of unlabeled dataThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet would you mind elaborating on this?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.