Information-Theoretic Neuro-Correlates Boost Evolution of Cognitive Systems

Entropy

Jory Schossau¹  Christoph Adami²  Arend Hintze¹  Christoph Salge³  Georg Martius³  Keyan Ghazi-Zahedi³ 

[1] Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USA;;BEACON Center for the Study of Evolution in Action, Michigan State University, East Lansing, MI 48824, USA;Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USA

关键词: genetic algorithm;    neuro-correlate;    markov brain;    evolution;    information theory;   

DOI  :  10.3390/e18010006

来源: mdpi

【 摘 要 】

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.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.