Does Training Lead to the Formation of Modules in Threshold Networks?
This paper addresses the question to determine the necessary conditions for the emergence of modules in the framework of artificial evolution. In particular, threshold networks are trained as controllers for robots able to perform two different tasks at the same time. It is shown that modules do not emerge under a wide set of conditions in our experimental framework. This finding supports the hypothesis that the emergence of modularity indeed depends upon the algorithm used for artificial evolution and the characteristics of the tasks.
KeywordsHide Node Random Network Robot Performance Small Network Training Scheme
This research used computational resources of the “Plateforme Technologique de Calcul Intensif (PTCI)” located at the University of Namur, Belgium, which is supported by the F.R.S.-FNRS. This paper presents research results of the Belgian Network DYSCO (Dynamical Systems, Control, and Optimisation), funded by the Interuniversity Attraction Poles Programme, initiated by the Belgian State, Science Policy Office.
- 5.Deb, K.: Multi-Objective Optimization using Evolutionary Algorithms. John Wiley and Sons Ltd, Chichester (2008)Google Scholar
- 7.Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley (1989)Google Scholar
- 9.Nicolay, D., Carletti, T.: Neural networks learning: Some preliminary results on heuristic methods and applications. In: Perotti, A., Di Caro, L. (eds.) DWAI@AI*IA, volume 1126 of CEUR Workshop Proceedings, pp. 30–40. CEUR-WS.org (2013)Google Scholar
- 10.Nicolay, D., Roli, A., Carletti, T.: Learning multiple conflicting tasks with artificial evolution. In Advances in Artificial Life and Evolutionary Computation, volume 445 of Communications in Computer and Information Science, pp. 127–139. Springer International Publishing (2014)Google Scholar
- 14.Villani, M., et al.: The detection of intermediate-level emergent structures and patterns. Adv. Artif. Life, ECAL 12, 372–378 (2013)Google Scholar
- 15.Villani, M. et al.: The search for candidate relevant subsets of variables in complex systems. Artificial Life, 2015. Accepted. Also available as arXiv:1502.01734