"Thought curvature", a possible path in the direction of Artificial General Intelligence?

Intriguingly, here is a Google Deepmind paper (September 2016) that like the paper of mine, entitled "Thought curvature" (May 2016), considers combining translation invariant, and translation variant paradigms (i.e. disentangling factors of variation), particularly in the regime of reinforcement learning, causal laws of physics, and manifolds: https://arxiv.org/abs/1606.05579

Separately, "Thought curvature", describes algebra that utilizes super-manifolds, instead of merely manifolds.

Given particular streams of evidence..., is a degree of the super-manifold structure a viable path in the direction of mankind's likely last invention, Artificial General Intelligence?

Edited August 31, 20178 yr by ProgrammingGodJordan