Parallel Computation Is ESS

TL;DR

This paper introduces a formal model of autonomous learning inspired by biological computation, demonstrating that parallel implementations of this model are evolutionarily stable, explaining the prevalence of parallelism in nature.

Contribution

It proposes a formal Turing Machine model for autonomous learning with add/delete rule tables and shows parallel implementations are evolutionarily stable.

Findings

Parallel implementations are evolutionarily stable.

Nature exhibits abundant parallel computation.

The model explains biological parallelism in learning.

Abstract

There are enormous amount of examples of Computation in nature, exemplified across multiple species in biology. One crucial aim for these computations across all life forms their ability to learn and thereby increase the chance of their survival. In the current paper a formal definition of autonomous learning is proposed. From that definition we establish a Turing Machine model for learning, where rule tables can be added or deleted, but can not be modified. Sequential and parallel implementations of this model are discussed. It is found that for general purpose learning based on this model, the implementations capable of parallel execution would be evolutionarily stable. This is proposed to be of the reasons why in Nature parallelism in computation is found in abundance.