Gary Marcus

Open letter to @ylecun: I have been explicit that I believe that symbol-manipulation is part of the solution to AGI; Hinton has ridiculed that idea. Where do you fit in? With me? W Hinton? If in between, where? The field would benefit from a clear statement of your view.https://twitter.com/tabithagold/status/1070736319901519876 …

I have expressed my position on this many, many times (including in the recent book "Architects of Intelligence"). But you still seem misunderstand it every time and to insist that we disagree, when we don't actually disagree that much. I'm tired of wasting my time.... 1/2.

... but here we go again 1. Whatever we do, DL is part of the solution 2. Hence reasoning will need to be compatible with DL 3. That means using vectors instead of symbols, and differentiable functions instead of logic. 4. This will require new architectural concepts. 2/2

...continued 5. The argument that "DL sucks" is simply wrong. DL is gradient-based optimization of multi-module system. That is not going away. 6. Supervised and reinforcement learning as they exist today are insufficient. .....

... 7. Something like self-supervised learning is necessary. Now.....