Next Article in Journal
Mechanical Fault Diagnosis of High Voltage Circuit Breakers Based on Wavelet Time-Frequency Entropy and One-Class Support Vector Machine
Next Article in Special Issue
Nonparametric Problem-Space Clustering: Learning Efficient Codes for Cognitive Control Tasks
Previous Article in Journal
Comprehensive Study on Lexicon-based Ensemble Classification Sentiment Analysis
Previous Article in Special Issue
Quantifying Emergent Behavior of Autonomous Robots
Article

Information-Theoretic Neuro-Correlates Boost Evolution of Cognitive Systems

by 1,2,*, 2,3 and 1,3,4
1
Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USA
2
BEACON Center for the Study of Evolution in Action, Michigan State University, East Lansing, MI 48824, USA
3
Department of Microbiology & Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA
4
Department of Integrative Biology, Michigan State University, East Lansing, MI 48824, USA
*
Author to whom correspondence should be addressed.
Academic Editors: Christoph Salge, Georg Martius, Keyan Ghazi-Zahedi and Daniel Polani
Entropy 2016, 18(1), 6; https://doi.org/10.3390/e18010006
Received: 1 July 2015 / Revised: 9 December 2015 / Accepted: 22 December 2015 / Published: 25 December 2015
(This article belongs to the Special Issue Information Theoretic Incentives for Cognitive Systems)
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. View Full-Text
Keywords: genetic algorithm; neuro-correlate; markov brain; evolution; information theory genetic algorithm; neuro-correlate; markov brain; evolution; information theory
Show Figures

Figure 1

MDPI and ACS Style

Schossau, J.; Adami, C.; Hintze, A. Information-Theoretic Neuro-Correlates Boost Evolution of Cognitive Systems. Entropy 2016, 18, 6. https://doi.org/10.3390/e18010006

AMA Style

Schossau J, Adami C, Hintze A. Information-Theoretic Neuro-Correlates Boost Evolution of Cognitive Systems. Entropy. 2016; 18(1):6. https://doi.org/10.3390/e18010006

Chicago/Turabian Style

Schossau, Jory, Christoph Adami, and Arend Hintze. 2016. "Information-Theoretic Neuro-Correlates Boost Evolution of Cognitive Systems" Entropy 18, no. 1: 6. https://doi.org/10.3390/e18010006

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop