Abstract
We argue that artificial development is an appropriate means of approaching complex systems engineering. Artificial development works via the inclusion of mechanisms that enhance the evolvability of a design space. Two of these mechanisms, regularities and adaptive feedback with the environment, are discussed. We concentrate on the less explored of the two: adaptive feedback. A concrete example is presented and applied to a simple artificial problem resembling vasculogenesis. It is shown that the use of a local feedback function substantively improves the efficacy of a machine learner on the problem. Further, inclusion of this adaptive feedback eliminates the sensitivity of the machine learner to a system parameter previously shown to correspond to problem hardness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
One proposed definition from Lipson defines “structural regularities” as an “inverse Kolmogorov complexity”, that is, the amount by which a structural description could be compressed by a Universal Turing Machine [26]. Unfortunately, Kolmogorov complexity is generally uncomputable, and simpler forms of compression are often poorly correlated [20]. Further, the attempt to approximate the Kolmogorov complexity of evolved designs does not figure largely in current AD literature. Thus, we believe that most authors are referencing something quite different from Lipson’s definition when discussing “regularities”.
References
Arthur, W.: The effect of development on the direction of evolution: toward a twenty-first century consensus. Evol. Dev. 6(4), 282–288 (2004)
Banzhaf, W., Pillay, N.: Why complex systems engineering needs biological development. Complexity 13(2), 12–21 (2007)
Britton, N., Brown, A.: An Illustrated Ora of the Northern United States, Canada and the British Possessions, vol. 2. C. Scribner’s Sons, New York (1913)
Coen, E.: The Art of Genes: How Organisms Make Themselves. Oxford University Press, Oxford (1999)
Crews, D., Bull, J.: Sex determination: some like it hot (and some don’t). Nature 451, 527–528 (2008). doi:10.1038/451527a
Dawkins, R.: Climbing Mount Improbable. W.W. Norton & Company, New York (1996)
Devert, A., Bredeche, N., Schoenauer, M.: Artificial ontogeny for truss structure design. In: IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, vol. 0, pp. 298–305 (2008). doi:10.1109/SASOW.2008.53
Federici, D., Downing, K.: Evolution and development of a multicellular organism: scalability, resilience, and neutral complexification. Artif. Life 12(3), 381–409 (2006)
Gilbert, S.F., Epel, D.: Ecological Developmental Biology: Integrating Epigenetics, Medicine, and Evolution. Sinauer Associates Inc., Sunderland (2009)
Gould, S.J.: The Structure of Evolutionary Theory. The Belknap Press of Harvard University Press, Cambridge (2002)
Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: GECCO ’96: Proceedings of the First Annual Conference on Genetic Programming, pp. 81–89. MIT Press, Cambridge, MA, USA (1996)
Harding, S., Miller, J.: The dead state: a comparison between direct and developmental encodings. In: GECCO ’06: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation (2006)
Hendrikse, J.L., Parsons, T., Hallgrmsson, B.: Evolvability as the proper focus of evolutionary developmental biology. Evol. Dev. 9(4), 393–401 (2007). doi:10.1111/j.1525-142X.2007.00176.x
Hornby, G.: Measuring, enabling and comparing modularity, regularity and hierarchy in evolutionary design. In: GECCO ’05: Proceedings of the 2005 Conference on Genetic and Evolutionary Computation, pp. 1729–1736. ACM, New York, NY, USA (2005). doi:10.1145/1068009.1068297
Huttenlocher, P.R.: Neural Plasticity: The Effects of Environment on the Development of the Cerebral Cortex. Harvard University Press, Cambridge (2002)
Ilachinski, A.: Cellular Automata: A Discrete Universe. World Scientific, Singapore (2001)
Kicinger, R., Arciszewski, T., Jong, K.A.D.: Morphogenic evolutionary design: cellular automata representations in topological structural design. In: Parmee I.C. (ed.) Adaptive Computing in Design and Manufacture VI. Springer-Verlag (2004)
Kicinger, R., Arciszewski, T., Jong, K.A.D.: Evolutionary computation and structural design: a survey of the state of the art. Comput. Struct. 83(23–24), 1943–1978 (2005)
Kowaliw, T.: A good number of forms fairly beautiful. Ph.D. thesis, Concordia University, Montréal, QC, Canada (2007)
Kowaliw, T.: Measures of complexity for artificial embryogeny. In: GECCO ’08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, pp. 843–850. ACM, New York, NY, USA (2008). doi:10.1145/1389095.1389259
Kowaliw, T., Banzhaf, W.: Augmenting artificial development with local fitness. In: Tyrrell A. (ed.) IEEE Congress on Evolutionary Computation (CEC), 2009, pp. 316–323. doi:10.1109/CEC.2009.4982964
Kowaliw, T., Grogono, P., Kharma, N.: Bluenome: a novel developmental model of artificial morphogenesis. In: Deb, K. et al. (eds.) GECCO ’04: Proceedings of the 6th Annual Conference on Genetic and Evolutionary Computation. Springer-Verlag (2004)
Kowaliw, T., Grogono, P., Kharma, N.: Environment as a spatial constraint on the growth of structural form. In: GECCO ’07: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, pp. 1037–1044. ACM, New York, NY, USA (2007). doi:10.1145/1276958.1277163
Kowaliw, T., Grogono, P., Kharma, N.: The evolution of structural form through artificial embryogeny. In: IEEE Symposium on Artificial Life, ALIFE ’07, pp. 425–432. IEEE (2007). doi:10.1109/ALIFE.2007.367826
Lindenmayer, A.: Mathematical models for cellular interaction in development. J. Theor. Biol. 18, 280–315 (1968)
Lipson, H.: Principles of modularity, regularity, and hierarchy for scalable systems. J. Biol. Phys. Chem. 7, 125–128 (2007)
Mech, R., Prusinkiewicz, P.: Visual models of plants interacting with their environment. In: SIGGRAPH ’96 Proceedings, vol. 30, pp. 397–410 (1996)
Merks, R., Roeland, M., Hoekstra, A., Kaandorp, J., Sloot, P., Hogeweg, P.: Problem-solving environments for biological morphogenesis. Comput. Sci. Eng. 8(1), 61–72 (2006). doi:10.1109/MCSE.2006.11
Miller, J.: Evolving a self-repairing, self-regulating, french flag organism. In: Deb, K. et al. (eds.) GECCO ’04: Proceedings of the 6th Annual Conference on Genetic and Evolutionary Computation, pp. 129–139. Springer-Verlag (2004)
Mulder, B.: On growth and force. Science 322, 1643–1644 (2008)
Newman, S.A., Forgacs, G., Müller, G.B.: Before programs: the physical origination of multicellular forms. Int. J. Dev. Biol. 50, 289–299 (2006). doi:10.1387/ijdb.052049sn
Rieffel, J., Pollack, J.: The emergence of ontogenic scaffolding in a stochastic development environment. In: Deb, K. et al. (eds.) GECCO ’04: Proceedings of the 6th Annual Conference on Genetic and Evolutionary Computation. Springer-Verlag (2004)
Sen, S., Day, A.: Modelling trees and their interaction with the environment: a survey. Comput. Graph. 29(5), 805–817 (2005). doi:10.1016/j.cag.2005.08.025
Seys, C., Beer, R.: Effect of encoding on the evolvability of an embodied neural network. In: GECCO ’06: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation (2006)
Stanley, K., D’Ambrosio, D., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009). doi:10.1162/artl.2009.15.2.15202
Steiner, T., Jin, Y., Sendhoff, B.: A cellular model for the evolutionary development of lightweight material with an inner structure. In: GECCO ’08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, pp. 851–858. ACM (2008). doi:10.1145/1389095.1389260
Tufte, G., Haddow, P.C.: Extending artificial development: exploiting environmental information for the achievement of phenotypic plasticity. In: Evolvable Systems: From Biology to Hardware (2007)
Turing, A.: The chemical basis of morphogenesis. Philos. Trans. Royal Soc. B 237, 37–72 (1952)
Wolpert, L., Dover, G.: Positional information and pattern formation. Philos. Trans. Royal Soc. Lond. Ser. B Biol. Sci. 295(1078), 441–450 (1981)
Yogev, O., Shapiro, A., Antonsson, E.: Modularity and symmetry in computational embryogeny. In: GECCO ’08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, pp. 1151–1152. ACM, New York, NY, USA (2008). doi:10.1145/1389095.1389323
Acknowledgments
TK and WB would like to thank Nature for billions of years of tireless effort. Smashing stuff! In addition, NSERC of Canada supported WB by Discovery Grant RGPIN 283304-07.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kowaliw, T., Banzhaf, W. (2012). Mechanisms for Complex Systems Engineering Through Artificial Development. In: Doursat, R., Sayama, H., Michel, O. (eds) Morphogenetic Engineering. Understanding Complex Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33902-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-33902-8_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33901-1
Online ISBN: 978-3-642-33902-8
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)