Evaluating evolution as a learning algorithm
Populations and Evolution
2023-09-25 v2 Adaptation and Self-Organizing Systems
Abstract
We interpret the Moran model of natural selection and drift as an algorithm for learning features of a simplified fitness landscape, specifically genotype superiority. This algorithm's efficiency in extracting these characteristics is evaluated by comparing it to a novel Bayesian learning algorithm developed using information-theoretic tools. This algorithm makes use of a communication channel analogy between an environment and an evolving population. We use the associated channel-rate to determine an informative population-sampling procedure. We find that the algorithm can identify genotype superiority faster than the Moran model but at the cost of larger fluctuations in uncertainty.
Keywords
Cite
@article{arxiv.2208.00911,
title = {Evaluating evolution as a learning algorithm},
author = {Miles Miller-Dickson and Christopher Rose and C. Brandon Ogbunugafor and I. Saira Mian},
journal= {arXiv preprint arXiv:2208.00911},
year = {2023}
}