The Holographic Principle: Why Deep Learning Works
Carlos E. Perez
2263

Also, something doesn't seem right here.

Article: "In other words, as you move from the bottom to the top of the network, the information entanglement increases".

I thought these networks were learning to disentangle factors of variation in latent space, not entangle them!

How do models learn by doing what appears to be the opposite of learning?