Anyone with a modicum of understanding of deep learning and intelligence knows that AGI is impossible unless we solve the unsupervised learning problem. UL is inherently non-symbolic and yet we have people like @GaryMarcus pushing the field toward symbolic AI. This is absurd.
please stop misrepresenting me. as you know I advocated both hybrid models and unsupervised learning (of a different sort than is popular) at the end of Deep Learning: A Critical Appraisal.
-
-
My point is that you can't have it both ways. Unsupervised learning is non-symbolic by definition. If one uses UL as part of an intelligent system, the entire system must be non-symbolic.
-
why? i don’t at all understand any of these assertions
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.