It's impossible (I think) for associationist string analysis to deduce a semantic representation that captures (even simple) logical force inference. [Examples are legion.] I literally can't understand why anyone believes this is a plausible path to human AI.
My hostility is not to deep learning, it’s to deep learning alone. I have been clear about the distinction for 26 years, and pointed you numerous times to places where I have clarified this, typically in > 140 characters.https://twitter.com/ylecun/status/1067008412842635264 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You & LeCun are pushing the field in the wrong direction. How many times must it be explained to you that, unlike the brain, a DNN cannot detect a pattern without a prior representation of it and that this is a fatal flaw? Why is this simple objection so hard for you 2 to grasp?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You are correct, Gary, in my admittedly limited 50+ yrs of
#AI investigation and invention. No single#AI#algorithm is ever "sufficient."
Here's an excellent example:
#SafetyFirst#datascience#machinelearning#bigdata#tech#IoT#Robotics#aiethics#NLP#DeepLearningpic.twitter.com/rAyrR7GMlO
- 1 more reply
New conversation -
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.