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.
-
-
-
Replying to @IntuitMachine
Functionalism is not a consensus position in neuroscience.
1 reply 0 retweets 4 likes -
Replying to @Plinz
Okay, perhaps this resistance makes sense for neuroscientists (
@tyrell_turing ) but what about machine learning folk? What's their excuse?1 reply 0 retweets 1 like -
Replying to @IntuitMachine @tyrell_turing
machine learning is basically predictive coding
2 replies 0 retweets 1 like -
Replying to @Plinz @IntuitMachine
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.
1 reply 1 retweet 2 likes -
Replying to @tyrell_turing @Plinz
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.
1 reply 0 retweets 1 like -
Replying to @IntuitMachine @tyrell_turing
It resolves once you notice that what you interpret as a representation of a past observation is itself an observable.
1 reply 0 retweets 2 likes -
Replying to @Plinz @tyrell_turing
What I mean is that the brain sees what it predicts and not the actual.
1 reply 0 retweets 0 likes
Yes, for the observer, there is never an actual.
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.