# Towards a Theory of Evolution as Multilevel Learning

arXiv: https://arxiv.org/abs/2110.14602 · HTML: https://mlsanity.com/paper/2110.14602/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 132 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 3 of 3)

- [The world as a neural network](https://mlsanity.com/paper/2008.01540/) (2020)
- [Towards a theory of machine learning](https://mlsanity.com/paper/2004.09280/) (2020)
- [Emergent Quantumness in Neural Networks](https://mlsanity.com/paper/2012.05082/) (2020)

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

- [Diffusion Models are Evolutionary Algorithms](https://mlsanity.com/paper/2410.02543/) (2024)
- [Supervised structure learning](https://mlsanity.com/paper/2311.10300/) (2023)
- [Towards a theory of quantum gravity from neural networks](https://mlsanity.com/paper/2111.00903/) (2021)
- [Thermodynamics of Evolution and the Origin of Life](https://mlsanity.com/paper/2110.15066/) (2021)
- [Heuristically Adaptive Diffusion-Model Evolutionary Strategy](https://mlsanity.com/paper/2411.13420/) (2024)
- [Dataset-learning duality and emergent criticality](https://mlsanity.com/paper/2405.17391/) (2024)
- [Arbitrary Order Meta-Learning with Simple Population-Based Evolution](https://mlsanity.com/paper/2303.09478/) (2023)
- [Emergent field theories from neural networks](https://mlsanity.com/paper/2411.08138/) (2024)
- [Distributionally Robust Free Energy Principle for Decision-Making](https://mlsanity.com/paper/2503.13223/) (2025)
- [Geometric Learning Dynamics](https://mlsanity.com/paper/2504.14728/) (2025)
- [Bio-inspired Machine Learning: programmed death and replication](https://mlsanity.com/paper/2207.04886/) (2022)
- [Control of Overfitting with Physics](https://mlsanity.com/paper/2412.10716/) (2024)
- [Molecular Learning Dynamics](https://mlsanity.com/paper/2504.10560/) (2025)
- [It's a super deal -- train recurrent network on noisy data and get smooth prediction free](https://mlsanity.com/paper/2206.04215/) (2022)
- [On Physical Origins of Learning](https://mlsanity.com/paper/2310.02375/) (2023)
- [CogNarr Ecosystem: Facilitating Group Cognition at Scale](https://mlsanity.com/paper/2407.18945/) (2024)
- [Geometric framework for biological evolution](https://mlsanity.com/paper/2603.15198/) (2026)
- [From Optimal Policies to Individual Differences: Rethinking Reinforcement Learning for Biology](https://mlsanity.com/paper/2607.16542/) (2026)

## Abstract (arXiv)

We apply the theory of learning to physically renormalizable systems in an attempt to develop a theory of biological evolution, including the origin of life, as multilevel learning. We formulate seven fundamental principles of evolution that appear to be necessary and sufficient to render a universe observable and show that they entail the major features of biological evolution, including replication and natural selection. These principles also follow naturally from the theory of learning. We formulate the theory of evolution using the mathematical framework of neural networks, which provides for detailed analysis of evolutionary phenomena. To demonstrate the potential of the proposed theoretical framework, we derive a generalized version of the Central Dogma of molecular biology by analyzing the flow of information during learning (back-propagation) and predicting (forward-propagation) the environment by evolving organisms. The more complex evolutionary phenomena, such as major transitions in evolution, in particular, the origin of life, have to be analyzed in the thermodynamic limit, which is described in detail in the accompanying paper.