I think their intention goes beyond producing just some esoteric math though .. (see the quote below (my emboldened bit) from the 'Discussion' section of their paper).I just don't understand what it means to say the universe 'is a neural network'. I suspect that what they are really saying is that it is possible to find aspects of the mathematics that describe the universe that have parallels with the mathematics that describe neural networks... ¯\_(ツ)_/¯
My point in bringing this up however, is that the evidence is that models are how we acquire knowledge and what 'they are trying to find out', (your words there), is which model best explains what we mean by 'universe' or 'nature' ... and never 'things' which exist independently from those models.
In this instance, the model of their universe is a 'neural network' model.
What they haven't realised yet though, is how 'the world around us actually works', if they were asked to describe what they mean by that, would generate their 'neural network' model.In this paper we discussed a possibility that the entire universe on its most fundamental level is a neural network. This is a very bold claim. We are not just saying that the artificial neural networks can be useful for analyzing physical systems or for discovering physical laws, we are saying that this is how the world around us actually works.
(Fyi): they go on:
With this respect it could be considered as a proposal for the theory of everything, and as such it should be easy to prove it wrong. All that is needed is to find a physical phenomenon which cannot be described by neural networks. Unfortunately (or fortunately) it is easer said than done. It turns out that the dynamics of neural networks is so complex that one can only understand it in very specific limits. The main objective of this paper was to describe the behavior of the neural networks in the limits when the relevant degrees of freedom (such as bias vector, weight matrix, state vector of neurons) can be modeled as stochastic variables which undergo a learning evolution. In this section we shall briefly discuss the main results and implications of the results for a possible emergence of quantum mechanics, general relativity and macroscopic observers from a microscopic neural network.
Upvote
0