[colorincorrect]

Perhaps this paper provides an explanation? https://arxiv.org/pdf/1608.08225.pdf

"The exceptional simplicity of physics-based functions hinges on properties such as symmetry, locality, compositionality and polynomial log-probability, and we explore how these properties translate into exceptionally simple neural networks approximating both natural phenomena such as images and abstract representations thereof such as drawings."

[xfs]

This is really good. Deep learning right now is giving off a kind of illusion of domain-independent general intelligence that can solve any problem, so it would be really helpful to have some theoretical characterization of the specific problem domains it's good at and ones it's not good at.

[pizza]

That was an interesting read - although I guess it would have been cool had they delved deeper into the brain/cognition aspect of the introduction a bit more..