ABSTRACT
A network is structurally modular if it can be divided into tightly connected groups which are weakly connected or disconnected from each other. Such networks are known to be capable of fast evolutionary adaptation, which makes modularity a highly desired property of networks involved in evolutionary computation. Modularity is known to correlate positively with another network parameter, sparsity. Based on this relationship, we hypothesize that starting evolution with a population of sparse networks should increase the modularity of the evolved networks. We find that this technique can enhance the performance of an existing technique for modularity evolution, multiobjective performance-connection cost (P&CC) optimization, and enable a multiobjective algorithm which maximizes performance and minimizes time since last mutation to produce modular solutions almost as efficiently as the P&CC optimization does.
- W. R. Ashby. Design for a brain. Wiley, 1952.Google Scholar
- V. D. Blondel, J.-L. Guillaume, R. Lambiotte, and E. Lefebvre. Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment, 2008(10):P10008, 2008.Google ScholarCross Ref
- J. C. Bongard. Spontaneous evolution of structural modularity in robot neural network controllers. In Proceedings of the 13th annual conference on Genetic and evolutionary computation, pages 251--258. ACM, 2011. Google ScholarDigital Library
- B. Calcott. Chaining distinct tasks drives the evolution of modularity. In ALIFE 14: The Fourteenth Conference on the Synthesis and Simulation of Living Systems, pages 701--702, 2014.Google ScholarCross Ref
- J. Clune, J.-B. Mouret, and H. Lipson. The evolutionary origins of modularity. Proceedings of the Royal Society b: Biological sciences, 280(1755):20122863, 2013.Google ScholarCross Ref
- C. Espinosa-Soto and A. Wagner. Specialization can drive the evolution of modularity. PLoS computational biology, 6(3):e1000719, 2010.Google Scholar
- M. Girvan and M. E. Newman. Community structure in social and biological networks. Proceedings of the National Academy of Sciences, 99(12):7821--7826, 2002.Google ScholarCross Ref
- N. Kashtan and U. Alon. Spontaneous evolution of modularity and network motifs. Proceedings of the National Academy of Sciences of the United States of America, 102(39):13773--13778, 2005.Google ScholarCross Ref
- J.-B. Mouret. Novelty-based multiobjectivization. In New horizons in evolutionary robotics, pages 139--154. Springer, 2011.Google ScholarCross Ref
- M. Schmidt and H. Lipson. Age-fitness pareto optimization. In Genetic Programming Theory and Practice VIII, pages 129--146. Springer, 2011.Google ScholarCross Ref
- K. O. Stanley and R. Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary computation, 10(2):99--127, 2002. Google ScholarDigital Library
- G. P. Wagner and L. Altenberg. Perspective: Complex adaptations and the evolution of evolvability. Evolution, pages 967--976, 1996.Google Scholar
Index Terms
- Exploiting the Relationship Between Structural Modularity and Sparsity for Faster Network Evolution
Recommendations
Constraining connectivity to encourage modularity in HyperNEAT
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationA challenging goal of generative and developmental systems (GDS) is to effectively evolve neural networks as complex and capable as those found in nature. Two key properties of neural structures in nature are regularity and modularity. While HyperNEAT ...
Emergence of modularity in genotype-phenotype mappings
A novel evolutionary method that allows us to study the emergence of modularity for genotype-phenotype mapping in the course of Darwinian evolution is described. The method is based on composite epigenotypes with two parts: a binary genotype; and a ...
Spontaneous evolution of structural modularity in robot neural network controllers: artificial life/robotics/evolvable hardware
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationIn order to evolve large robot controllers for increasingly complex tasks, fully connected neural networks are not feasible. However, manually designing sparse neural connectivity is not intuitive, and thus should be placed under evolutionary control. ...
Comments