Toward a theory of evolution as multilevel learning

We apply the theory of learning to physically renormalizable systems in an attempt to outline 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. It is shown that these cornerstone phenomena of biology emerge from the fundamental features of learning dynamics such as the existence of a loss function, which is minimized during learning. We then sketch 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 paper by Vanchurin et al.

Automated summary

This study applies the theory of learning to physically renormalizable systems in order to outline a theory of biological evolution, including the origin of life, as a multilevel learning process. Seven fundamental principles are formulated to explain the major features of biological evolution, including replication and natural selection. The mathematical framework of neural networks is used to analyze evolutionary phenomena with a detailed focus, and a generalized version of the Central Dogma of molecular biology is derived by analyzing information flow during learning and predicting the environment through evolving organisms.