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.
-
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.
