Complexity-based speciation and genotype representation for neuroevolution

TL;DR

This paper presents Cortex, a neuroevolution framework that uses complexity-based speciation and a novel genotype representation to improve diversity, resilience to bloat, and network evaluation efficiency.

Contribution

It introduces a new speciation principle based on network complexity and a zero-redundancy genotype representation for neuroevolution.

Findings

Demonstrates competitive performance of Cortex in experiments

Provides a flexible, reproducible platform for neuroevolution research

Enhances diversity and robustness in evolving neural networks

Abstract

This paper introduces a speciation principle for neuroevolution where evolving networks are grouped into species based on the number of hidden neurons, which is indicative of the complexity of the search space. This speciation principle is indivisibly coupled with a novel genotype representation which is characterised by zero genome redundancy, high resilience to bloat, explicit marking of recurrent connections, as well as an efficient and reproducible stack-based evaluation procedure for networks with arbitrary topology. Furthermore, the proposed speciation principle is employed in several techniques designed to promote and preserve diversity within species and in the ecosystem as a whole. The competitive performance of the proposed framework, named Cortex, is demonstrated through experiments. A highly customisable software platform which implements the concepts proposed in this study is also introduced in the hope that it will serve as a useful and reliable tool for experimentation in the field of neuroevolution.