I am annoyed by the idea of "predictive coding" in neuroscience, not because it is wrong but because it is trivially true, and understood at least since the 1960ies.
-
-
That’s overly broad... doesn’t actually apply to the specific Rao & Ballard model. But yes, you can demonstrate that the cost function used in predictive coding is no different in principle from those used in many ML applications.
-
This I hesitate to make the leap. There is a difference between a model that predicts future observations and one that classifies what it observes.
- 3 more replies
New conversation -
-
-
It has been referred to as Software 2.0.
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.