When the software world wants to build stuff that works, it still mostly uses stuff that innately incorporates symbol-manipulation. Can someone please show me an operating system, a word processor, a spreadsheet or scaleable DB that is built with neural networks and no symbols?https://twitter.com/tyrell_turing/status/1003313227852181504 …
-
Your premise is wrong: I not dissing neural networks. I AM saying that they are not a desert topping and a floor wax.https://www.nbc.com/saturday-night-live/video/shimmer-floor-wax/n8625 …
@bruce_lambert you are straw-manning me, too, as i constantly argue for hybrid models and suggest that utility of deep learning lies in perceptual categorization. read anything i have written lately, or back to 1992.
-
-
Perhaps I’m misconstruing your arguments, but your recent paper isn’t titled “In Defense of Hybrid Systems” or “The Fragility of Symbol Systems.” It’s “Deep Learning: A Critical Appraisal.”
-
perhaps you should read beyond the title? at least the abstract, say? just a thought.
End of conversation
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.