Information-theoretic neuro-correlates boost evolution of cognitive systems
arXiv:1511.07962 · doi:10.3390/e18010006
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.
arXiv comment26 pages, 6 figures plus 3 Suppl. figures (included). To appear in special issue "Information Theoretic Incentives for Cognitive Systems" of journal "Entropy"
References in corpus (10)
- The evolutionary origins of modularity
- Network information and connected correlations
- The Value of Information for Populations in Varying Environments
- Predator confusion is sufficient to evolve swarming behavior
- Integrated information increases with fitness in the evolution of animats
- The evolution of representation in simple cognitive networks
- Exploring the evolution of a trade-off between vigilance and foraging in group-living organisms
- Wiring cost in the organization of a biological network
- Quantifying the role of population subdivision in evolution on rugged fitness landscapes
- Computational evolution of decision-making strategies