"Taking the world to consist of discrete intelligible mesoscale objects is an *achievement* of intelligence, not a premise on top of which intelligence runs." -- Brian Cantwell Smith, from The Promise of Artificial Intelligence
Show this thread
-
Not so sure about that, he explicitly discounts hybrid models because they don't resolve the underlying philosophical issues with symbolic methods
just to be clear: 1. hybrid vs pure deep learning vs pure symbols or some other option and 2. innate vs learned vs both are somewhat separate questions. my own bets of course are innate rough draft + lots of learning with both stats and symbols.
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.