We don’t encounter writings that seek to change reality very often.

Vitaly Vanchurin, a physics professor at the University of Minnesota Duluth, attempts to reframe reality in a particularly eye-opening way in a preprint sent to arXiv this summer. He suggests that humans are part of a vast brain network that controls everything in our environment. In other words, it’s “possible that the entire cosmos on its most fundamental level is a neural network,” he stated in the report.

Physicists have been working to make quantum physics and general relativity compatible for a long time. The former contends that time is relative and connected to the structure of space-time, whereas the latter asserts that time is universal and absolute.

Vanchurin contends in his research that both universal theories can “display approximation behaviours” in artificial neural networks. He adds that since quantum mechanics “is a highly successful paradigm for representing physical processes on a wide range of scales, it is widely thought that on the most basic level the entire universe is regulated by the rules of quantum mechanics and even gravity should somehow originate from it.”

In the paper’s discussion, it is said that “we are not only claiming that the artificial neural networks can be beneficial for evaluating physical systems or for uncovering physical laws, we are saying that this is how the world around us actually works.” It may be argued that this is a proposal for the theory of everything, and as such, it should be simple to disprove.

Most of the physicists and machine learning specialists we contacted declined to comment on the topic on the record due to their scepticism about the paper’s findings. However, Vanchurin dug into the debate and expanded on his proposal in a Q&A with Futurism.

Futurism: According to your paper, the universe might be fundamentally a neural network. How would you justify your conclusions to someone who was unfamiliar with physics or neural networks?

Theodore Vanchurin: Your question might be answered in two different ways.

The first method is to begin with an accurate model of a neural network before examining how the network behaves when there are many more neurons present. What I’ve demonstrated is that quantum mechanical equations very accurately capture the behaviour of a system close to equilibrium, while classical mechanical equations accurately capture the behaviour of a system farther from equilibrium. Coincidence? Perhaps, but as far as we are aware, the physical world operates according to quantum and classical mechanics.

Starting with physics is the second approach. We are aware that general relativity operates rather effectively at vast sizes and that quantum mechanics operates fairly well at tiny scales, but we have not yet been able to integrate the two theories. This is referred to as the quantum gravity problem. We obviously have a significant gap in our knowledge, and to make matters worse, we have no idea how to deal with observers. In terms of quantum mechanics and cosmology, this is referred to as the measurement problem, respectively.

Then, one might contend that quantum physics, general relativity, and observers are the three phenomena that require unification, not just two. Most scientists (99%) would agree that quantum mechanics is the fundamental theory and that all else should somehow flow from it, but no one is certain how it can be accomplished. In this paper, I explore a different hypothesis: that everything, including quantum mechanics, general relativity, and macroscopic observers, arises from a tiny neural network that serves as the fundamental structure. Things seem fairly decent so far.

Who or what initially thought of this?

I first produced a paper titled “Towards a theory of machine learning” in order to simply understand deep learning better. The initial plan was to analyse neural network activity using statistical mechanics techniques, but it turned out that, within certain bounds, neural network learning (or training) dynamics are extremely comparable to the quantum dynamics we observe in physics. I chose to investigate the notion that the physical universe is actually a neural network at the time since I was (and still am) on sabbatical leave. The notion is undoubtedly absurd, but is it truly absurd enough to be true? That is still up in the air.

You stated in the report that all it took to disprove the theory was to identify a physical fact that neural networks could not adequately explain. Why do you say that, exactly? Why is it “easier said than done” to do this?

There are a lot of “theories of everything,” but the majority of them must be false. According to my hypothesis, everything you see around you is a neural network; therefore, all that is required to disprove it is the discovery of a phenomenon that cannot be explained by a neural network. However, if you stop to think about it, it is a really challenging undertaking, especially given how little we truly understand about how neural networks behave and how machine learning functions. That’s why I initially tried to construct a theory of machine learning.

The notion is undoubtedly absurd, but is it truly absurd enough to be true? That is still up in the air.

Does your research take the observer effect into account, and how does it relate to quantum mechanics?

Everett’s (or many-worlds) interpretation and Bohm’s (or hidden variables) interpretation are the two primary schools of thought about quantum physics. Regarding the many-worlds interpretation, I have nothing new to add, but I think I can add to the ideas of hidden variables. The states of individual neurons are the hidden variables in the emergent quantum mechanics that I researched, whereas quantum variables (such as the bias vector and weight matrix) are the trainable variables. The concealed variables may be extremely non-local, which would violate Bell’s inequalities. The system does not need to be local because every neuron can link to every other neuron, notwithstanding the assumption of an estimated space-time locality.

Could you please clarify the relationship between this concept and natural selection? The evolution of intricate biological cells and structures is influenced by natural selection.

I’m saying something very simple. The microscopic neural network is composed of both more and less stable components (or subnetworks). Evolution would favour the more robust structures, causing the less robust ones to disappear. I anticipate that natural selection will produce extremely simple structures at the smallest scales, such as chains of neurons, but increasingly complicated structures at larger scales. The claim is that everything we see around us (particles, atoms, cells, observers, etc.) is the outcome of natural selection since I see no reason why this process should be restricted to a particular length scale.

I was interested when you said in your first email that you might not understand everything yourself. What did you mean specifically? Were you talking about the complexity of the neural network or something deeper?

I am indeed referring to the complexity of neural networks. I didn’t even have time to think about how the results might be philosophically significant.

Does this theory suggest that we are residing in a simulation, I have a question?

No, we do not realise that we are part of a cerebral network.