Towards a Theory of Evolution as Multilevel Learning

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.

29 pages, 3 figures

References in corpus (1)

• Collective evolution and the genetic code

Cited by in corpus (9)

• A variational synthesis of evolutionary and developmental dynamics
• The Free Energy Principle drives neuromorphic development
• Evolution is Driven by Natural Autoencoding: Reframing Species, Interaction Codes, Cooperation, and Sexual Reproduction
• Reconstruction of classical skyrmions from Anderson towers: quantum Darwinism in action
• Distributed Evolution Strategies with Multi-Level Learning for Large-Scale Black-Box Optimization
• Cooperative Coevolution for Non-Separable Large-Scale Black-Box Optimization: Convergence Analyses and Distributed Accelerations
• Thermodynamics of Evolution and the Origin of Life
• Control of Overfitting with Physics
• Emergence of global receptive fields capturing multipartite quantum correlations