# The world as a neural network

arXiv: https://arxiv.org/abs/2008.01540 · HTML: https://mlsanity.com/paper/2008.01540/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 18 of 18)

- [Machine-Learning Mathematical Structures](https://mlsanity.com/paper/2101.06317/) (2021)
- [Towards a Theory of Evolution as Multilevel Learning](https://mlsanity.com/paper/2110.14602/) (2021)
- [Towards a theory of quantum gravity from neural networks](https://mlsanity.com/paper/2111.00903/) (2021)
- [The Autodidactic Universe](https://mlsanity.com/paper/2104.03902/) (2021)
- [Thermodynamics of Evolution and the Origin of Life](https://mlsanity.com/paper/2110.15066/) (2021)
- [Dataset-learning duality and emergent criticality](https://mlsanity.com/paper/2405.17391/) (2024)
- [Emergent field theories from neural networks](https://mlsanity.com/paper/2411.08138/) (2024)
- [QKSA: Quantum Knowledge Seeking Agent](https://mlsanity.com/paper/2107.01429/) (2021)
- [Autonomous particles](https://mlsanity.com/paper/2301.10077/) (2023)
- [Covariant Gradient Descent](https://mlsanity.com/paper/2504.05279/) (2025)
- [p-Adic Statistical Field Theory and Deep Belief Networks](https://mlsanity.com/paper/2207.13877/) (2022)
- [Geometric Learning Dynamics](https://mlsanity.com/paper/2504.14728/) (2025)
- [Self-organized criticality in neural networks](https://mlsanity.com/paper/2107.03402/) (2021)
- [Bio-inspired Machine Learning: programmed death and replication](https://mlsanity.com/paper/2207.04886/) (2022)
- [A Survey of Quantum-Cognitively Inspired Sentiment Analysis Models](https://mlsanity.com/paper/2306.03608/) (2023)
- [Molecular Learning Dynamics](https://mlsanity.com/paper/2504.10560/) (2025)
- [Verifying Good Regulator Conditions for Hypergraph Observers: Natural Gradient Learning from Causal Invariance via Established Theorems](https://mlsanity.com/paper/2603.09067/) (2026)
- [Geometric framework for biological evolution](https://mlsanity.com/paper/2603.15198/) (2026)

## Abstract (arXiv)

We discuss a possibility that the entire universe on its most fundamental level is a neural network. We identify two different types of dynamical degrees of freedom: "trainable" variables (e.g. bias vector or weight matrix) and "hidden" variables (e.g. state vector of neurons). We first consider stochastic evolution of the trainable variables to argue that near equilibrium their dynamics is well approximated by Madelung equations (with free energy representing the phase) and further away from the equilibrium by Hamilton-Jacobi equations (with free energy representing the Hamilton's principal function). This shows that the trainable variables can indeed exhibit classical and quantum behaviors with the state vector of neurons representing the hidden variables. We then study stochastic evolution of the hidden variables by considering D non-interacting subsystems with average state vectors, barbf x1, ..., barbf xD and an overall average state vector barbf x0. In the limit when the weight matrix is a permutation matrix, the dynamics of barbf xμ can be described in terms of relativistic strings in an emergent D+1 dimensional Minkowski space-time. If the subsystems are minimally interacting, with interactions described by a metric tensor, then the emergent space-time becomes curved. We argue that the entropy production in such a system is a local function of the metric tensor which should be determined by the symmetries of the Onsager tensor. It turns out that a very simple and highly symmetric Onsager tensor leads to the entropy production described by the Einstein-Hilbert term. This shows that the learning dynamics of a neural network can indeed exhibit approximate behaviors described by both quantum mechanics and general relativity. We also discuss a possibility that the two descriptions are holographic duals of each other.