Evolutionary morphogenesis for multi-cellular systems

Article

Abstract

With a gene required for each phenotypic trait, direct genetic encodings may show poor scalability to increasing phenotype length. Developmental systems may alleviate this problem by providing more efficient indirect genotype to phenotype mappings. A novel classification of multi-cellular developmental systems in evolvable hardware is introduced. It shows a category of developmental systems that up to now has rarely been explored. We argue that this category is where most of the benefits of developmental systems lie (e.g. speed, scalability, robustness, inter-cellular and environmental interactions that allow fault-tolerance or adaptivity). This article describes a very simple genetic encoding and developmental system designed for multi-cellular circuits that belongs to this category. We refer to it as the morphogenetic system. The morphogenetic system is inspired by gene expression and cellular differentiation. It focuses on low computational requirements which allows fast execution and a compact hardware implementation. The morphogenetic system shows better scalability compared to a direct genetic encoding in the evolution of structures of differentiated cells, and its dynamics provides fault-tolerance up to high fault rates. It outperforms a direct genetic encoding when evolving spiking neural networks for pattern recognition and robot navigation. The results obtained with the morphogenetic system indicate that this “minimalist” approach to developmental systems merits further study.

Keywords

Evolutionary computation Developmental system Genotype to phenotype mapping Evolvable hardware Neural network 

References

  1. 1.
    L. Altenberg, “The evolution of evolvability,” in Advances in Genetic Programming, K. Kinnear (ed.), MIT Press: Cambridge, MA, 1994, pp. 47–74.Google Scholar
  2. 2.
    P. J. Angeline, “Morphogenic evolutionary computations: Introduction, issues and examples,” in The Fourth Annual Conference on Evolutionary Programming, J. R. McDonnel, R. G. Reynolds and D. B. Fogel (eds.), MIT Press: Cambridge, MA, 1995, pp. 387–401.Google Scholar
  3. 3.
    J. C. Astor and C. Adami, “A developmental model for the evolution of artificial neural networks,” Artificial Life, vol. 6, pp. 189–218, 2000.Google Scholar
  4. 4.
    W. Banzhaf and J. Miller, “The challenge of complexity,” in Frontiers of Evolutionary Computation, volume 11 of Genetic Algorithms And Evolutionary Computation Series, A. Menon (ed.), Kluwer Academic Publishers: Boston, MA, USA, chapter 11, 2004, pp. 73–99.Google Scholar
  5. 5.
    P. J. Bentley, “Fractal proteins,” Genetic Programming and Evolvable Machines, vol. 5, pp.71–101, 2004.Google Scholar
  6. 6.
    P. J. Bentley and S. Kumar, “Three ways to grow designs: A comparison of embryogenies for an evolutionary design problem,” in Proceeding of Genetic and Evolutionary Computation Conference, W. Banzhaf, J. Daida, A. E. Eiben, M. H. Garzon, V. Honavar, M. Jakiela, and R. E. Smith (eds.), Morgan Kaufmann: San Francisco, CA, 1999, pp. 35–43.Google Scholar
  7. 7.
    E. J. W. Boers and H. Kuiper, “Biological metaphors and the design of modular artificial neural networks,” Master's thesis, Department of Computer Science and Experimental and Theoretical Psychology, Leiden University: The Netherlands, 1992.Google Scholar
  8. 8.
    J. C. Bongard and R. Pfeifer, “Evolving complete agents using artificial ontogeny,” in Morpho-Functional Machines: The New Species (Designing Embodied Intelligence), F. Hara and R. Pfeifer, (eds.), Springer-Verlag: Heidelberg, 2003, pp. 237–258.Google Scholar
  9. 9.
    C. A. Coello, A. H. Aguirre, and B. P. Buckles, “Evolutionary multiobjective design of combinational logic circuits,” in 2nd NASA/DoD Workshop on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2000, pp. 161–170.Google Scholar
  10. 10.
    E. Coen, The Art of Genes, Oxford University Press: Oxford, 1999.Google Scholar
  11. 11.
    H. de Garis, Genetic Programming: GenNets, Artificial Nervous Systems, Artificial Embryos. PhD thesis, Brussels University, 1992.Google Scholar
  12. 12.
    H. de Garis, “Growing an artificial brain with a million neural net modules inside a trillion cell cellular automaton machine,” in Proceedings of the Fourth International Symposium on Micro Machine and Computer Science, 1993, pp. 211–214.Google Scholar
  13. 13.
    H. de Garis, L. de Penning, A. Buller, and D. Decesare, “Early experiments on the CAM-brain machine (CBM),” in 1st NASA/DoD Workshop on Evolvable Hardware, A. Stoica et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2001, pp. 211–219.Google Scholar
  14. 14.
    F. Dellaert and R. Beer, “A developmental model for the evolution of complete autonomous agents,” in Proceedings of the 4th International Conference on Simulation of Adaptive Behavior, P. Maes, M. J. Mataric, J.-A. Meyer, J. Pollack and S. Wilson (eds.), MIT Press-Bradford Books: Cambridge, MA, 1996, pp. 393–401.Google Scholar
  15. 15.
    E. A. Di Paolo, “Spike timing dependent plasticity for evolved robots,” Adaptive Behavior, vol. 10, pp. 243–263, 2002.Google Scholar
  16. 16.
    P. Eggenberger, “Cell interactions as a control tool of developmental processes for evolutionary robotics,” in Proceedings of the 4th International Conference on Simulation of Adaptive Behavior, P. Maes, M. J. Mataric, J.-A. Meyer, J. Pollack, and S. Wilson (eds.), MIT Press-Bradford Books: Cambridge, MA, 1996, pp. 440–448.Google Scholar
  17. 17.
    P. Eggenberger, “Creation of neural networks based on developmental and evolutionary principles,” in Proceedings of the International Conference on Artificial Neural Networks ICANN’97, W. Gerstner, A. Germond, M. Hasler, and J.-D. Nicoud (eds.), Springer-Verlag: Heidelberg, 1997, pp. 337–342.Google Scholar
  18. 18.
    P. Eggenberger, “Evolving morphologies of simulated 3D organisms based on differential gene expression,” in Proceedings of the 4th European Conference on Artificial Life (ECAL97), P. Husbands and I. Harvey (eds.), MIT Press: Cambridge, MA, 1997, pp. 205–213.Google Scholar
  19. 19.
    D. Federici, “Evolving a neurocontroller through a process of embryogeny,” in Proceedings of the 8th International Conference on Simulation of Adaptive Behavior, S. Schaal, A. Ijspeert, A. Billard, S. Vijayakumar, J. Hallam, and J.-A. Meyer (eds.), MIT Press-Bradford Book: Cambridge, MA, 2004, pp. 373–382.Google Scholar
  20. 20.
    D. Federici, “Using embryonic stages to increase the evolvability of development,” in Proceedings of WORLDS Workshop at GECCO 2004, 2004.Google Scholar
  21. 21.
    D. Floreano and C. Mattiussi, “Evolution of spiking neural controllers for autonomous vision-based robots,” in Evolutionary Robotics IV, T. Gomi (ed.), Springer-Verlag: Heidelberg, 2001, pp. 38–61.Google Scholar
  22. 22.
    D. Floreano and F. Mondada, “Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot,” in Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior, D. Cliff, P. Husbands, J. Meyer, and S. W. Wilson (eds.), MIT Press-Bradford Books: Cambridge, MA, 1994, pp. 421–430.Google Scholar
  23. 23.
    D. Floreano, N. Schoeni, G. Caprari, and J. Blynel, “Evolutionary bits’n’spikes,” in Proceedings of Artificial Life VIII, R. K. Standish, M. A. Bedau, and H. A. Abbass (eds.), MIT Press: Cambridge, MA, 2002, pp. 335–344.Google Scholar
  24. 24.
    W. Gerstner and W. Kistler, Spiking Neuron Models, Cambridge University Press, 2002.Google Scholar
  25. 25.
    D. E. Goldberg, Genetic Algorithms in Search Optimization & Machine Learning, Addison-Wesley: Reading, MA, 1989.Google Scholar
  26. 26.
    R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley: Reading, MA, 1993.Google Scholar
  27. 27.
    T. Gordon, “Exploring models of development for evolutionary circuit design,” in Congress on Evolutionary Computation (CEC2003), IEEE Press, 2003, pp. 2050–2057.Google Scholar
  28. 28.
    T. Gordon and P. Bentley, “Bias and scalability in evolutionary development,” in Proceedings of the 2005 Genetic and Evolutionary Computation Conference, ACM Press, 2005, pp. 83–90.Google Scholar
  29. 29.
    T. Gordon and P. Bentley, “Development brings scalability to hardware evolution,” in 2005 NASA/DoD Conference on Evolvable Hardware, J. Lohn et al. (ed.), IEEE Computer Society Press: Los Alamitos, CA, 2005, pp. 272–279.Google Scholar
  30. 30.
    F. Gruau, Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm. PhD thesis, Laboratoire de l’Informatique du Parallélisme, Ecole Normale Supérieure de Lyon, France, 1994.Google Scholar
  31. 31.
    P. C. Haddow, G. Tufte, and P. van Remortel, “Shrinking the Genotype: L-systems for EHW?,” in Proceedings of the 4th International Conference on Evolvable Systems (ICES 2001), Y. Liu et al. (eds.), Springer-Verlag: Heidelberg, 2001, pp. 128–139.Google Scholar
  32. 32.
    P. C. Haddow and P. van Remortel, “From here to there: Future robust EHW technologies for large digital designs,” in 3rd NASA/DoD Workshop on Evolvable Hardware, D. Keymeulen et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2001, pp. 232–239.Google Scholar
  33. 33.
    G. Hartmann, G. Frank, G. Schäfer, and M. Wolff, “SPIKE128K-An accelerator for dynamic simulation of large pulse-coded networks,” in Proceedings of MicroNeuro 97, Dresden, 1997, pp. 130–139.Google Scholar
  34. 34.
    T. Higuchi, et al., “Evolving hardware with genetic learning: A first step towards building a Darwin machine,” in Proceedings of the 2nd International Conference on Simulation of Adaptive Behaviour, J.-A. Meyer, H. Roitblat, and S. Wilson (eds.), MIT Press-Bradford Books: Cambridge, MA, 1993, pp. 417–424.Google Scholar
  35. 35.
    T. Higuchi, M. Iwata, D. Keymeulen, H. Sakanashi, M. Murakawa, I. Kajitani, E. Takahashi, K. Toda, M. Salami, N. Kajihara, and N. Otsu, “Real-world applications of analog and digital evolvable hardware,” IEEE Transactions on Evolutionary Computation, vol. 3, pp. 220–235, 1999.Google Scholar
  36. 36.
    G. S. Hornby and J. B. Pollack, “Evolving L-systems to generate virtual creatures,” Computers and Graphics, vol. 25, pp. 1041–1048, 2001.Google Scholar
  37. 37.
    G. Indiveri and R. Douglas, “ROBOTIC VISION: Neuromorphic vision sensors,” Science, vol. 288, pp. 1189–1190, 2000.Google Scholar
  38. 38.
    N. Jakobi, Harnessing morphogenesis. Technical Report CSRP 423, School of Cognitive and Computing Sciences, University of Sussex, 1995.Google Scholar
  39. 39.
    I. Kajitani, T. Hoshino, D. Nishikawa, H. Yokoi, S. Nakaya, T. Yamauchi, T. Inuo, N. Kajihara, M. Iwata, D. Keymeulen, and T. Higuchi, “A gate-level EHW chip: implementing GA operations and reconfigurable hardware on a single LSI,” in Proceedings of the 2nd International Conference on Evolvable Systems (ICES 98), M. Sipper et al. (eds.), Springer-Verlag, Heidelberg, 1998, pp. 1–12.Google Scholar
  40. 40.
    T. Kalganova, “Bidirectional incremental evolution in extrinsic evolvable hardware,” in 2nd NASA/DoD Workshop on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2000, pp. 65–74.Google Scholar
  41. 41.
    S. A. Kauffman, “Metabolic stability and epigenesis in randomly constructed genetic nets,” Journal of Theoretical Biology, vol. 22, pp. 437–467, 1969.Google Scholar
  42. 42.
    S. Kazadi, Y. Qi, I. Park, N. Huang, P. Hwu, B. Kwan, W. Lue, and H. Li, “Insufficiency of piecewise evolution,” in 3rd NASA/DoD Workshop on Evolvable Hardware, D. Keymeulen et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2001, pp. 223–231.Google Scholar
  43. 43.
    D. Keymeulen, R. Zebulum, Y. Jin, and A. Stoica, “Fault-tolerant evolvable hardware using field-programmable transistor arrays,” IEEE Transactions on Reliability, vol. 49, pp. 305–316, 2000.Google Scholar
  44. 44.
    H. Kitano, “Designing neural networks using genetic algorithms with graph generation system,” Complex Systems, vol. 4, pp. 461–476, 1990.Google Scholar
  45. 45.
    H. Kitano, “Challenges of evolvable systems: Analysis and future directions,” in Proceedings of the 1st International Conference on Evolvable Systems (ICES 96), T. Higuchi et al. (eds.), Springer-Verlag: Heidelberg, 1996, pp. 125–135.Google Scholar
  46. 46.
    J. Kodjabachian and J.-A. Meyer, “Evolution and development of control architectures in animats,” Robotics and Autonomous Systems, vol. 16, pp. 161–182, 1995.Google Scholar
  47. 47.
    A. Koopman and D. Roggen, “Evolving genetic regulatory networks for hardware fault tolerance,” in Proceedings of Parallel Problem Solving from Nature VIII, X. Yao, E. Burke, J. A. Lozano, J. Smith, J. J. Merelo-Guervós, J. A. Bullinaria, J. Rowe, P. Tiňo, A. Kab´n, and H.-P. Schwefel (eds.), Springer-Verlag: Heidelberg, 2004, pp. 561–570.Google Scholar
  48. 48.
    J. R. Koza, Genetic Programming, MIT Press, Cambridge, MA, 1992.Google Scholar
  49. 49.
    S. Kumar and P. J. Bentley, “Biologically inspired evolutionary development,” in Proceedings of the 5th International Conference on Evolvable Systems (ICES 2003), A. M. Tyrrell et al. (eds.), Springer-Verlag: Heidelberg, 2003, pp. 57–68.Google Scholar
  50. 50.
    S. Kumar and P. J. Bentley, On Growth, Form and Computers, Academic Press: London, UK, 2003.Google Scholar
  51. 51.
    P. K. Lehre and P. C. Haddow, “Developmental mappings and phenotypic complexity,” in Congress on Evolutionary Computation (CEC2003), IEEE Press, 2003, pp. 62–68.Google Scholar
  52. 52.
    A. Lindenmayer, “Mathematical models for cellular interactions in development,” Journal of Theoretical Biology, vol. 18, pp. 280–299, 1968.Google Scholar
  53. 53.
    H. Liu, J. Miller, and A. Tyrrell, “A biological development model for the design of robust multiplier,” in Applications of Evolutionary Computing: EvoHot, G. Drechsler, R. Squillero (eds.), Springer-Verlag: Heidelberg, 2005, pp. 195–204.Google Scholar
  54. 54.
    H. Liu, J. F. Miller, and A. M. Tyrrell, “An intrinsic robust transient fault-tolerant developmental model for digital systems,” in Proceedings of WORLDS workshop at GECCO 2004, 2004.Google Scholar
  55. 55.
    S. Luke and L. Spector, “Evolving graphs and networks with edge encoding: Preliminary report,” in Late Breaking Papers at the Genetic Programming 1996 Conference, J. R. Koza (ed.), 1996, pp. 117–124.Google Scholar
  56. 56.
    D. Mange, M. Sipper, A. Stauffer, and G. Tempesti, “Toward robust integrated circuits: The embryonics approach,” in Proceedings of the IEEE, vol. 88, pp. 516–541, 2000.Google Scholar
  57. 57.
    P. Marchal, C. Piguet, D. Mange, A. Stauffer, and S. Durand, “Embryological development on silicon,” in Proceedings of Artificial Life IV, R. Brooks and P. Maes (eds.), MIT Press, 1994, pp. 365–370.Google Scholar
  58. 58.
    C. Mattiussi and D. Floreano, “Evolution of analog networks using local string alignment on highly reorganizable genomes,” in 2004 NASA/DoD Conference on Evolvable Hardware, R. Zebulum et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2004, pp. 30–37.Google Scholar
  59. 59.
    J. F. Miller, “Evolving developmental programs for adaptation, morphogenesis, and self-repair,” in Proceedings of 7th European Conference on Artificial Life, W. Banzhaf, T. Christaller, P. Dittrich, J. T. Kim, and J. Ziegler (eds.), Springer-Verlag: Heidelberg, 2003, pp. 256–265.Google Scholar
  60. 60.
    E. Mjolsness, D. H. Sharp, and B. K. Alpert, “Scaling, machine learning, and genetic neural nets,” Advances in Applied Mathematics, vol. 10, pp. 137–163, 1989.Google Scholar
  61. 61.
    F. Mondada, E. Franzi, and P. Ienne, “Mobile robot miniaturisation: A tool for investigation in control algorithms,” in Proceedings of the 3rd International Symposium on Experimental Robotics, Springer-Verlag: Heidelberg, 1994, pp. 501–513.Google Scholar
  62. 62.
    C. L. Nehaniv, “Evolvability,” BioSystems, vol. 69, pp. 77–81, 2003.Google Scholar
  63. 63.
    S. Nolfi and D. Parisi, Growing neural networks. Technical report, Institute of Psychology, Rome, 1992.Google Scholar
  64. 64.
    T. Quick, C. L. Nehaniv, K. Dautenhahn, and G. Roberts, “Evolving embodied genetic regulatory network-driven control systems,” in Proceedings of the 7th European Conference on Artificial Life (ECAL2003), W. Banzhaf, T. Christaller, P. Dittrich, J. T. Kim, and J. Ziegler (eds.), Springer-Verlag: Heidelberg, 2003, pp. 266–277Google Scholar
  65. 65.
    D. Roggen, Multi-Cellular Reconfigurable Circuits: Evolution, Morphogenesis and Learning, PhD thesis, EPFL, Lausanne, Switzerland, 2005.Google Scholar
  66. 66.
    D. Roggen and D. Federici, “Multi-cellular development: is there scalability and robustness to gain?,” in Proceedings of Parallel Problem Solving from Nature VIII, X. Yao, E. Burke, J. A. Lozano, J. Smith, J. J. Merelo-Guervós, J. A. Bullinaria, J. Rowe, P. Tiňo, A. Kab´n, and H.-P. Schwefel (eds.), Springer-Verlag: Heidelberg, 2004, pp. 391–400.Google Scholar
  67. 67.
    D. Roggen and D. Floreano, “Hardware morphogenetic developmental system,” Technical report, Laboratory of Intelligent Systems, EPFL, Lausanne, Switzerland, http://lis.epfl.ch/publications.php, 2004.Google Scholar
  68. 68.
    D. Roggen, D. Floreano, and C. Mattiussi, “A morphogenetic evolutionary system: Phylogenesis of the POEtic tissue,” in Proceedings of the 5th International Conference on Evolvable Systems (ICES 2003), A. M. Tyrrell et al. (eds), Springer-Verlag: Heidelberg, 2003, pp. 153–164.Google Scholar
  69. 69.
    D. Roggen, S. Hofmann, Y. Thoma, and D. Floreano, “Hardware spiking neural network with run-time reconfigurable conectivity in an autonomous robot,” in 2003 NASA/DoD Conference on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2003, pp. 189–198.Google Scholar
  70. 70.
    A. G. Rust, Developmental Self-Organisation in Artificial Neural Networks. PhD thesis, Dept. of Computer Science, University of Hertfordshire, 1998.Google Scholar
  71. 71.
    D. Salomon, Data Compression: The Complete Reference, Springer-Verlag: Heidelberg, 2004.Google Scholar
  72. 72.
    T. Schoenauer, S. Atasoy, N. Mehrtash, and H. Klar, “NeuroPipe-Chip: A digital neuro-processor for spiking neural networks,” IEEE Transactions on Neural Networks, vol. 13, pp. 205–213, 2002.Google Scholar
  73. 73.
    K. Sims, “Evolving 3D morphology and behavior by competition,” in Proceedings of the Artificial Life IV, R. Brooks and P. Maes (eds.), MIT Press: Cambridge, MA, 1994, pp. 28–39.Google Scholar
  74. 74.
    T. Smith, P. Husbands, and M. O’Shea, “Not measuring evolvability: Initial investigation of an evolutionary robotics search space,” in Congress on Evolutionary Computation (CEC2001), IEEE Press, 2001, pp. 9–16.Google Scholar
  75. 75.
    K. Stanley and R. Miikkulainen, “Evolving neural networks through augmenting topologies,” Evolutionary Computation, vol. 10, pp. 99–127, 2002.Google Scholar
  76. 76.
    K. Stanley and R. Miikkulainen, “A taxonomy for artificial embryogeny,” Artificial Life, vol. 9, pp. 93–130, 2003.Google Scholar
  77. 77.
    F. Streichert, C. Spieth, H. Ulmer, and A. Zell, “How to evolve the head-tail pattern from reaction-diffusion systems,” in 2004 NASA/DoD Conference on Evolvable Hardware, R. Zebulum et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2004, pp. 261–268.Google Scholar
  78. 78.
    G. Tempesti, D. Mange, E. Petraglio, A. Stauffer, and Y. Thoma, “Developmental processes in silicon: An engineering perspective,” in 2003 NASA/DoD Conference on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2003, pp. 255–264.Google Scholar
  79. 79.
    A. Thompson, “An evolved circuit, intrinsic in silicon, entwined with physics,” in Proceedings of the 1st International Conference on Evolvable Systems (ICES 96), T. Higuchi et al. (eds.), Springer-Verlag: Heidelberg, 1996, pp. 390–405.Google Scholar
  80. 80.
    A. Thompson, I. Harvey, and P. Husbands, “Unconstrained evolution and hard consequences,” in Towards Evolvable Hardware, E. Sanchez and M. Tomassini (eds.), Springer-Verlag: Heidelberg, 1996, pp. 136–165.Google Scholar
  81. 81.
    O. Torres, J. Eriksson, J. M. Moreno, and A. Villa, “Hardware optimization of a novel spiking neuron model for the POEtic tissue,” in Proceedings of the IWANN’03, J. Mira (ed.), Springer-Verlag: Heidelberg, 2003, pp. 113–120.Google Scholar
  82. 82.
    G. Tufte and P. C. Haddow, “Biologically-inspired: A rule-based self-reconfiguration of a virtex chip,” in Proceedings of the 4th International Conference on Computational Science (ICCS 2004), M. Bubak, G. D. van Albada, P. M. A. Sloot, et al. (eds.), Springer-Verlag: Heidelberg, 2004, pp. 1249–125.Google Scholar
  83. 83.
    A. M. Turing, “The chemical basis of morphogenesis,” Philosophical Transactions of the Royal Society of London, B, vol. 237, pp. 37–72, 1952.Google Scholar
  84. 84.
    A. M. Tyrrell, E. Sanchez, D. Floreano, G. Tempesti, D. Mange, J.-M. Moreno, J. Rosenberg, and A. Villa, “POEtic tissue: An integrated architecture for bio-inspired hardware,” in Proceedings of the 5th International Conference on Evolvable Systems (ICES 2003), A. M. Tyrrell et al. (eds.), Springer-Verlag: Heidelberg, 2003, pp. 129–140.Google Scholar
  85. 85.
    J. Vaario, S. Ohsuga, and K. Hori, “Connectionist modeling using Lindenmayer systems,” in Information Modeling and Knowledge Bases: Foundations, Theory, and Applications, Ohsuga et al. (eds.), IOS Press, 1991, pp. 496–510.Google Scholar
  86. 86.
    V. K. Vassilev, D. Job, and J. F. Miller, “Towards the automatic design of more efficient digital circuits,” in 2nd NASA/DoD Workshop on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2000, pp. 151–160.Google Scholar
  87. 87.
    V. K. Vassilev and J. F. Miller, “Scalability problems of digital circuit evolution: Evolvability and efficient designs,” in 2nd NASA/DoD Workshop on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society Press: Los Alamitos, CA, 2000, pp. 55–64.Google Scholar
  88. 88.
    G. P. Wagner and L. Altenberg, “Complex adaptations and the evolution of evolvability,” Evolution, vol. 50, pp. 967–976, 1996.Google Scholar
  89. 89.
    L. Wolpert, “Do we understand development?,” Science, vol. 266, pp. 571–572, 1994.Google Scholar
  90. 90.
    L. Wolpert, Principles of Development, Oxford University Press: Oxford, 1998.Google Scholar
  91. 91.
    X. Yao, “A review of evolutionary artificial neural networks,” International Journal of Intelligent Systems, vol. 4, pp. 203–222, 1993.Google Scholar
  92. 92.
    X. Yao and T. Higuchi, “Promises and challenges of evolvable hardware,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 29, pp. 87–97, 1999.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  • Daniel Roggen
    • 1
    • 2
  • Diego Federici
    • 3
    • 4
  • Dario Floreano
    • 1
  1. 1.Laboratory of Intelligent SystemsÉcole Polytechnique Fédérale de LausanneLausanneSwitzerland
  2. 2.Wearable Computing LaboratoryETH ZürichZürichSwitzerland
  3. 3.Department of Computer and Information SciencesNorwegian University of Science and TechnologyTrondheimNorway
  4. 4.Google’s Zürich European Engineering CentreZürichSwitzerland

Personalised recommendations