Towards a Theory of Evolution as Multilevel Learning

TL;DR

This paper proposes a novel theoretical framework viewing biological evolution as multilevel learning, using neural network principles to explain evolution's fundamental features and predict complex phenomena like the origin of life.

Contribution

It introduces seven fundamental principles of evolution derived from learning theory, unifying biological evolution with neural network models and providing a basis for analyzing complex evolutionary events.

Findings

Derives a generalized Central Dogma from learning principles

Predicts information flow during evolution using neural network analysis

Links major evolutionary transitions to thermodynamic limits

Abstract

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.