Information-theoretic neuro-correlates boost evolution of cognitive systems

TL;DR

This paper introduces information-theoretic neuro-correlates that, when combined with fitness objectives, enhance genetic algorithms' ability to evolve neural controllers for complex cognitive tasks.

Contribution

It proposes and empirically tests neuro-correlates based on information theory to improve the evolutionary search for high-performing neural systems.

Findings

Neuro-correlates help GAs find higher peaks in rugged fitness landscapes.

Information-theoretic measures improve evolution of neural controllers for cognitive tasks.

Neuro-correlates significantly aid in solving tasks requiring memory and information integration.

Abstract

Genetic Algorithms (GA) are a powerful set of tools for search and optimization that mimic the process of natural selection, and have been used successfully in a wide variety of problems, including evolving neural networks to solve cognitive tasks. Despite their success, GAs sometimes fail to locate the highest peaks of the fitness landscape, in particular if the landscape is rugged and contains multiple peaks. Reaching distant and higher peaks is difficult because valleys need to be crossed, in a process that (at least temporarily) runs against the fitness maximization objective. Here we propose and test a number of information-theoretic (as well as network-based) measures that can be used in conjunction with a fitness maximization objective (so-called ``neuro-correlates") to evolve neural controllers for two widely different tasks: a behavioral task that requires information integration, and a cognitive task that requires memory and logic. We find that judiciously chosen neuro-correlates can significantly aid GAs to find the highest peaks.