Evolving Ensembles: What Can We Learn from Biological Mutualisms?

Ensembles are groups of classifiers which cooperate in order to reach a decision. Conventionally, the members of an ensemble are trained sequentially, and typically independently, and are not brought together until the final stages of ensemble generation. In this paper, we discuss the potential benefits of training classifiers together, so that they learn to interact at an early stage of their development. As a potential mechanism for achieving this, we consider the biological concept of mutualism, whereby cooperation emerges over the course of biological evolution. We also discuss potential mechanisms for implementing this approach within an evolutionary algorithm context.

[1]  Kenneth Sörensen,et al.  Metaheuristics - the metaphor exposed , 2015, Int. Trans. Oper. Res..

[2]  Marc T. J. Johnson,et al.  Adaptive Evolution in Ecological Communities , 2012, PLoS biology.

[3]  Jordi Bascompte,et al.  Plant-Animal Mutualistic Networks: The Architecture of Biodiversity , 2007 .

[4]  F. C. Santos,et al.  The role of diversity in the evolution of cooperation. , 2012, Journal of theoretical biology.

[5]  Andrew M. Tyrrell,et al.  A co-evolutionary framework for regulatory motif discovery , 2007, 2007 IEEE Congress on Evolutionary Computation.

[6]  Stephen L. Smith,et al.  A comparison of evolved linear and non-linear ensemble vote aggregators , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[7]  Stephen L. Smith,et al.  Forming classifier ensembles with multimodal evolutionary algorithms , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[8]  Larry Bull,et al.  Applications of Learning Classifier Systems , 2004 .

[9]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

[10]  Norbert Schuff,et al.  Evolving classifiers to inform clinical assessment of Parkinson's disease , 2013, 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE).

[11]  Larry Bull,et al.  Learning Classifier Systems: A Brief Introduction , 2004 .

[12]  Arjen Biere,et al.  Three‐way interactions between plants, microbes and insects , 2013 .

[13]  Susan Stepney,et al.  Biochemical connectionism , 2013, Natural Computing.

[14]  Susan Stepney,et al.  Computational models of signalling networks for non-linear control , 2013, Biosyst..

[15]  Andy M Tyrrell,et al.  Modelling biological evolvability: implicit context and variation filtering in enzyme genetic programming. , 2004, Bio Systems.

[16]  Xin Yao,et al.  Large scale evolutionary optimization using cooperative coevolution , 2008, Inf. Sci..

[17]  Lee Spector,et al.  Cultural transmission of information in genetic programming , 1996 .

[18]  B. Wang,et al.  Phylogenetic distribution and evolution of mycorrhizas in land plants , 2006, Mycorrhiza.

[19]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[20]  John E. Stewart,et al.  The direction of evolution: The rise of cooperative organization , 2014, Biosyst..

[21]  Andrew M. Tyrrell,et al.  Evolving Classifiers to Recognize the Movement Characteristics of Parkinson's Disease Patients , 2014, IEEE Transactions on Evolutionary Computation.