Coordinated inference, Holographic neural networks, and quantum error correction

Abstract

Coordinated inference problems are being introduced as a basis for a neural network representation of the locality problem in the holographic bulk. It is argued that a type of problem originating in the "prisoners and hats" dilemma involves certain non-local structures to be found in the AdS/CFT duality. The neural network solution to this problem introduces a new approach that can be flexible enough to identify holographic dualities beyond AdS/CFT. Neural networks are shown to have a significant role in the connection between the bulk and the boundary, being capable of inferring sufficient information capable of explaining the pre-arrangement of observables in the bulk that would lead to non-local precursor operators in the boundary.