Advertisement

Evolving Programs to Build Artificial Neural Networks

  • Julian F. MillerEmail author
  • Dennis G. Wilson
  • Sylvain Cussat-Blanc
Chapter
Part of the Emergence, Complexity and Computation book series (ECC, volume 35)

Abstract

In general, the topology of Artificial Neural Networks (ANNs) is human-engineered and learning is merely the process of weight adjustment. However, it is well known that this can lead to sub-optimal solutions. Topology and Weight Evolving Artificial Neural Networks (TWEANNs) can lead to better topologies however, once obtained they remain fixed and cannot adapt to new problems. In this chapter, rather than evolving a fixed structure artificial neural network as in neuroevolution, we evolve a pair of programs that build the network. One program runs inside neurons and allows them to move, change, die or replicate. The other is executed inside dendrites and allows them to change length and weight, be removed, or replicate. The programs are represented and evolved using Cartesian Genetic Programming. From the developed networks multiple traditional ANNs can be extracted, each of which solves a different problem. The proposed approach has been evaluated on multiple classification problems.

References

  1. 1.
    Aljundi, R., Chakravarty, P., Tuytelaars, T.: Expert gate: lifelong learning with a network of experts 2 (2016). CoRR. arXiv:1611.06194
  2. 2.
    Astor, J.C., Adami, C.: A development model for the evolution of artificial neural networks. Artificial Life 6, 189–218 (2000)CrossRefGoogle Scholar
  3. 3.
    Balaam, A.: Developmental neural networks for agents. In: Advances in Artificial Life, Proceedings of the 7th European Conference on Artificial Life (ECAL 2003), pp. 154–163. Springer (2003)Google Scholar
  4. 4.
    Belew, R.K.: Interposing an ontogenic model between genetic algorithms and neural networks. In: S.J. Hanson, J.D. Cowan, C.L. Giles (eds.) Advances in neural information processing systems NIPS5, pp. 99–106. Morgan Kaufmann (1993)Google Scholar
  5. 5.
    Boers, E.J.W., Kuiper, H.: Biological metaphors and the design of modular neural networks. Master’s thesis, Dept. of Computer Science and Dept. of Experimental and Theoretical Psychology, Leiden University (1992)Google Scholar
  6. 6.
    Cangelosi, A., Nolfi, S., Parisi, D.: Cell division and migration in a ‘genotype’ for neural networks. Netw.-Comput. Neural Syst. 5, 497–515 (1994)CrossRefGoogle Scholar
  7. 7.
    Deacon, T.: The Symbolic Species: The Co-evolution of Language and the Brain. W.W. Norton and Company, New York (1998)Google Scholar
  8. 8.
    Dekaban, A.S., Sadowsky, D.: Changes in brain weights during the span of human life. Ann. Neurol. 4, 345–356 (1978)CrossRefGoogle Scholar
  9. 9.
    Downing, K.L.: Supplementing evolutionary developmental systems with abstract models of neurogenesis. In: Proceedings of the Conference on Genetic and Evolutionary Computation, pp. 990–996 (2007)Google Scholar
  10. 10.
    Drchal, J., Šnorek, M.: Tree-based indirect encodings for evolutionary development of neural networks. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) Artificial Neural Networks - ICANN, pp. 839–848. Springer, Berlin (2008)Google Scholar
  11. 11.
    Edelman, G., Tononi, G.: A Universe of Consciousness. Basic Books, New York (2000)Google Scholar
  12. 12.
    Eggenberger, P.: Creation of neural networks based on developmental and evolutionary principles. In: Gerstner, W., Germond, A., Hasler, M., Nicoud J.D. (eds.) Artificial Neural Networks — ICANN’97, pp. 337–342 (1997)Google Scholar
  13. 13.
    Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Advances in Neural Information Processing Systems, pp. 524–532 (1990)Google Scholar
  14. 14.
    Federici, D.: A regenerating spiking neural network. Neural Netw. 18(5–6), 746–754 (2005)CrossRefGoogle Scholar
  15. 15.
    Fernández-Delgado, M., Cernadas, E., Barro, S., Amorim, D.: Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learn. Res. 15(1), 3133–3181 (2014)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Ferreira, C.: Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence, 2nd edn. Springer, New York (2006)zbMATHGoogle Scholar
  17. 17.
    Floreano, D., Urzelai, J.: Neural morphogenesis, synaptic plasticity, and evolution. Theory Biosci. 120(3), 225–240 (2001)CrossRefGoogle Scholar
  18. 18.
    Franco, L., Jerez, J.M.: Constructive Neural Networks, vol. 258. Springer, Berlin (2009)CrossRefGoogle Scholar
  19. 19.
    French, R.M.: Catastrophic forgetting in connectionist networks: causes, consequences and solutions. Trends Cogn. Sci. 3(4), 128–135 (1999)CrossRefGoogle Scholar
  20. 20.
    Goldman, B.W., Punch, W.F.: Reducing wasted evaluations in cartesian genetic programming. In: Proceedings of the Genetic Programming: 16th European Conference, EuroGP 2013, Vienna, Austria, April 3–5, 2013, pp. 61–72. Springer, Berlin (2013)Google Scholar
  21. 21.
    Goldman, B.W., Punch, W.F.: Analysis of cartesian genetic programmings evolutionary mechanisms. IEEE Trans. Evol. Comput. 19, 359–373 (2015)CrossRefGoogle Scholar
  22. 22.
    Gruau, F.: Automatic definition of modular neural networks. Adapt. Behav. 3, 151–183 (1994)CrossRefGoogle Scholar
  23. 23.
    Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: Proceedings of Conference on Genetic Programming, pp. 81–89 (1996)Google Scholar
  24. 24.
    Hampton, A.N., Adami, C.: Evolution of robust developmental neural networks. In: Pollack, J., Bedau, M.A., Husbands, P., Ikegami, T., Watson R. (eds.) Proceedings of Artificial Life IX, pp. 438–443 (2004)Google Scholar
  25. 25.
    Harding, S., Miller, J.F., Banzhaf, W.: Developments in cartesian genetic programming: self-modifying cgp. Genet. Program. Evolvable Mach. 11(3–4), 397–439 (2010)CrossRefGoogle Scholar
  26. 26.
    Hornby, G., Lipson, H., Pollack, J.B.: Generative representations for the automated design of modular physical robots. IEEE Trans. Robot. Autom. 19, 703–719 (2003)CrossRefGoogle Scholar
  27. 27.
    Hornby, G.S., Pollack, J.B.: Creating high-level components with a generative representation for body-brain evolution. Artif. Life 8(3) (2002)Google Scholar
  28. 28.
    Huizinga, J., Clune, J., Mouret, J.B.: Evolving neural networks that are both modular and regular: HyperNEAT plus the connection cost technique. In: Proceedings of the Conference on Genetic and Evolutionary Computation, pp. 697–704 (2014)Google Scholar
  29. 29.
    Isles, A.: Neural and behavioral epigenetics; what it Is, and what is hype. Wiley (2015)Google Scholar
  30. 30.
    Jakobi, N.: Harnessing morphogenesis, COGS Research Paper 423. University of Sussex, Technical report (1995)Google Scholar
  31. 31.
    Jung, S.Y.: A topographical method for the development of neural networks for artificial brain evolution. Artif. Life 11, 293–316 (2005)CrossRefGoogle Scholar
  32. 32.
    Kandel, E.R., Schwartz, J.H., Jessell, T.M.: Principles of Neural Science, 4th edn. McGraw-Hill, New York (2000)Google Scholar
  33. 33.
    Khan, G.M.: Evolution of Artificial Neural Development - In Search of Learning Genes. Studies in Computational Intelligence, vol. 725. Springer, Berlin (2018)CrossRefGoogle Scholar
  34. 34.
    Khan, G.M., Miller, J.F.: In search of intelligence: evolving a developmental neuron capable of learning. Connect. Sci. 26(4), 297–333 (2014)CrossRefGoogle Scholar
  35. 35.
    Khan, G.M., Miller, J.F., Halliday, D.M.: Evolution of cartesian genetic programs for development of learning neural architecture. Evol. Comput. 19(3), 469–523 (2011)CrossRefGoogle Scholar
  36. 36.
    Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Syst. 4, 461–476 (1990)zbMATHGoogle Scholar
  37. 37.
    Kleim, J.A., Lussnig, E., Schwartz, E.R., Comery, T.A., Greenough, W.T.: Synaptogenesis and fos expression in the motor cortex of the adult rat after motor skill learning. J. Neurosci. 16, 4529–4535 (1996)CrossRefGoogle Scholar
  38. 38.
    Kleim, J.A., Vij, K., Ballard, D.H., Greenough, W.T.: Learning-dependent synaptic modifications in the cerebellar cortex of the adult rat persist for at least four weeks. J. Neurosci. 17, 717–721 (1997)CrossRefGoogle Scholar
  39. 39.
    Kodjabachian, J., Meyer, J.A.: Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects. IEEE Trans. Neural Netw. 9, 796–812 (1998)CrossRefGoogle Scholar
  40. 40.
    Koutník, J., Gomez, F., Schmidhuber, J.: Evolving neural networks in compressed weight space. In: Proceedings of the Conference on Genetic and Evolutionary Computation (GECCO-10) (2010)Google Scholar
  41. 41.
    Kumar, S., Bentley, P. (eds.): On Growth, Form and Computers. Academic Press (2003)Google Scholar
  42. 42.
    Luke, S., Spector, L.: Evolving graphs and networks with edge encoding: preliminary report. In: Late Breaking Papers at the Genetic Programming Conference, pp. 117–124 (1996)Google Scholar
  43. 43.
    Maguire, E.A., Gadian, D.G., Johnsrude, I.S., Good, C.D., Ashburner, J., Frackowiak, R.S.J., Frith, C.D.: Navigation-related structural change in the hippocampi of taxi drivers. PNAS 97, 4398–4403 (2000)CrossRefGoogle Scholar
  44. 44.
    McCloskey, M., Cohen, N.: Catastrophic interference in connectionist networks: the sequential learning problem. Psychol. Learn. Motiv. 24, 109–165 (1989)CrossRefGoogle Scholar
  45. 45.
    McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)MathSciNetCrossRefGoogle Scholar
  46. 46.
    Métin, C., Vallee, R., Rakic, P., Bhide, P.: Modes and mishaps of neuronal migration in the mammalian brain. Neuroscience 28, 11746–11752 (2008)CrossRefGoogle Scholar
  47. 47.
    Miller, J.F.: What bloat? cartesian genetic programming on boolean problems. In: Proceedings of the Conference on Genetic and Evolutionary Computation, Late Breaking Papers, pp. 295–302 (2001)Google Scholar
  48. 48.
    Miller, J.F. (ed.): Cartesian Genetic Programming. Springer, Berlin (2011)Google Scholar
  49. 49.
    Miller, J.F., Smith, S.L.: Redundancy and computational efficiency in cartesian genetic programming. IEEE Trans. Evol. Comput. 10(2), 167–174 (2006)CrossRefGoogle Scholar
  50. 50.
    Miller, J.F., Thomson, P.: Cartesian genetic programming. In: Proceedings of European Conference on Genetic Programming. LNCS, vol. 10802, pp. 121–132 (2000)Google Scholar
  51. 51.
    Miller, J.F., Thomson, P.: A developmental method for growing graphs and circuits. In: Proceedings of the International Conference on Evolvable Systems. LNCS, vol. 2606, pp. 93–104 (2003)Google Scholar
  52. 52.
    Miller, J.F., Wilson, D.G., Cussat-Blanc, S.: Evolving developmental programs that build neural networks for solving multiple problems. In: Banzhaf, W., Spector, L., Sheneman L. (eds.) Genetic Programming Theory and Practice XVI, Chap. TBC. Springer (2019)Google Scholar
  53. 53.
    Ooyen, A.V. (ed.): Modeling Neural Development. MIT Press, Cambridge (2003)Google Scholar
  54. 54.
    Rakic, P.: Principles of neural cell migration. Experientia 46, 882–891 (1990)CrossRefGoogle Scholar
  55. 55.
    Ratcliff, R.: Connectionist models of recognition and memory: constraints imposed by learning and forgetting functions. Psychol. Rev. 97, 205–308 (1990)CrossRefGoogle Scholar
  56. 56.
    Risi, S., Lehman, J., Stanley, K.O.: Evolving the placement and density of neurons in the HyperNEAT substrate. In: Proceedings of the Conference on Genetic and Evolutionary Computation, pp. 563–570 (2010)Google Scholar
  57. 57.
    Risi, S., Stanley, K.O.: Indirectly encoding neural plasticity as a pattern of local rules. In: From Animals to Animats 11: Conference on Simulation of Adaptive Behavior (2010)Google Scholar
  58. 58.
    Risi, S., Stanley, K.O.: Enhancing ES-HyperNEAT to evolve more complex regular neural networks. In: Proceedings of the Conference on Genetic and Evolutionary Computation, pp. 1539–1546 (2011)Google Scholar
  59. 59.
    Roggen, D., Federici, D., Floreano, D.: Evolutionary morphogenesis for multi-cellular systems. Genet. Program. Evolvable Mach. 8(1), 61–96 (2007)CrossRefGoogle Scholar
  60. 60.
    Rose, S.: The Making of Memory: From Molecules to Mind. Vintage (2003)Google Scholar
  61. 61.
    Rust, A., Adams, R., Bolouri, H.: Evolutionary neural topiary: growing and sculpting artificial neurons to order. In: Proceedings of the Conference on the Simulation and synthesis of Living Systems, pp. 146–150 (2000)Google Scholar
  62. 62.
    Rusu, A.A., Rabinowitz, N.C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., Hadsell, R.: Progressive neural networks (2016). arXiv:1606.04671
  63. 63.
    Ryan, C., Collins, J.J., Neill, M.O.: Grammatical evolution: evolving programs for an arbitrary language. In: Banzhaf, W., Poli, R., Schoenauer, M., Fogarty, T.C. (eds.) Genetic Programming, pp. 83–96. Springer, Berlin (1998)Google Scholar
  64. 64.
    Sharkey, A.J.: Combining artificial neural nets: ensemble and modular multi-net systems. Springer Science & Business Media (2012)Google Scholar
  65. 65.
    Siddiqi, A.A., Lucas, S.M.: A comparison of matrix rewriting versus direct encoding for evolving neural networks. In: Proceedings IEEE International Conference on Evolutionary Computation Proceedings, pp. 392–397 (1998)Google Scholar
  66. 66.
    Smythies, J.: The Dynamic Neuron. MIT Press, Cambridge (2002)CrossRefGoogle Scholar
  67. 67.
    Stanley, K., Miikkulainen, R.: Efficient evolution of neural network topologies. Proc. Congr. Evol. Comput. 2, 1757–1762 (2002)Google Scholar
  68. 68.
    Stanley, K.O.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program. Evolvable Mach. 8, 131–162 (2007)CrossRefGoogle Scholar
  69. 69.
    Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009)CrossRefGoogle Scholar
  70. 70.
    Stanley, K.O., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artif. Life 9(2), 93–130 (2003)CrossRefGoogle Scholar
  71. 71.
    Suchorzewski, M., Clune, J.: A novel generative encoding for evolving modular, regular and scalable networks. In: Proceedings of the Conference on Genetic and Evolutionary Computation, pp. 1523–1530 (2011)Google Scholar
  72. 72.
    Terekhov, A.V., Montone, G., ORegan, J.K.: Knowledge transfer in deep block-modular neural networks. In: Conference on Biomimetic and Biohybrid Systems, pp. 268–279. Springer (2015)Google Scholar
  73. 73.
    Tierney, A., Nelson III, C.: Brain development and the role of experience in the early years. Zero Three 30, 9–13 (2009)Google Scholar
  74. 74.
    Tramontin, A.D., Brenowitz, E.: Seasonal plasticity in the adult brain. Trends Neurosci. 23, 251–258 (2000)CrossRefGoogle Scholar
  75. 75.
    Tsankova, N., Renthal, W., Kumar, A., Nestler, E.: Epigenetic regulation in psychiatric disorders. Nat. Rev. Neurosci. 8(5), 33–367 (2007)CrossRefGoogle Scholar
  76. 76.
    Turner, A.J., Miller, J.F.: Cartesian genetic programming encoded artificial neural networks: a comparison using three benchmarks. In: Proceedings of the Conference on Genetic and Evolutionary Computation (GECCO), pp. 1005–1012 (2013)Google Scholar
  77. 77.
    Turner, A.J., Miller, J.F.: Recurrent cartesian genetic programming. In: Proceedings of the Parallel Problem Solving from Nature, pp. 476–486 (2014)Google Scholar
  78. 78.
    Valverde, F.: Rate and extent of recovery from dark rearing in the visual cortex of the mouse. Brain Res. 33, 1–11 (1971)CrossRefGoogle Scholar
  79. 79.
    Vassilev, V.K., Miller, J.F.: The advantages of landscape neutrality in digital circuit evolution. In: Proceedings of the International Conference on Evolvable Systems. LNCS, vol. 1801, pp. 252–263. Springer (2000)Google Scholar
  80. 80.
    Yerushalmi, U., Teicher, M.: Evolving synaptic plasticity with an evolutionary cellular development model. PLOS One 3(11), e3697 (2008)CrossRefGoogle Scholar
  81. 81.
    Yu, T., Miller, J.F.: Neutrality and the evolvability of Boolean function landscape. In: Proceedings of the European Conference on Genetic Programming. LNCS, vol. 2038, pp. 204–217 (2001)Google Scholar
  82. 82.
    Zar, J.H.: Biostatistical Analysis, 2nd edn. Prentice Hall, Upper Saddle River (1984)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Julian F. Miller
    • 1
    Email author
  • Dennis G. Wilson
    • 2
  • Sylvain Cussat-Blanc
    • 2
  1. 1.University of YorkHeslington, YorkUK
  2. 2.University of Toulouse, IRIT - CNRS - UMR5505ToulouseFrance

Personalised recommendations