Advertisement

Neuro-Centric and Holocentric Approaches to the Evolution of Developmental Neural Networks

  • Julian F. Miller
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 557)

Abstract

In nature, brains are built through a process of biological development in which many aspects of the network of neurons and connections change and are shaped by external information received through sensory organs. From numerous studies in neuroscience, it has been demonstrated that developmental aspects of the brain are intimately involved in learning. Despite this, most artificial neural network (ANN) models do not include developmental mechanisms and regard learning as the adjustment of connection weights. Incorporating development into ANNs raises fundamental questions. What level of biological plausibility should be employed? In this chapter, we discuss two artificial developmental neural network models with differing degrees of biological plausibility. One takes the view that the neuron is fundamental (neuro-centric) so that all evolved programs are based at the level of the neuron, the other carries out development at an entire network level and evolves rules that change the network (holocentric). In the process, we hope to reveal some important issues and questions that are relevant to researchers wishing to create other such models.

Keywords

Artificial Neural Network Genetic Programming Computational Function General Learning Dendrite Branch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    W.S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophy. 5, 115–133 (1943)Google Scholar
  2. 2.
    E.R. Kandel, J.H. Schwartz, T.M. Jessell, Principles of Neural Science, 4th edn. (McGraw-Hill, New York, 2000)Google Scholar
  3. 3.
    R.M. French, Catastrophic forgetting in connectionist networks: causes, consequences and solutions. Trends Cogn. Sci. 3(4), 128–135 (1999)CrossRefMathSciNetGoogle Scholar
  4. 4.
    M. McCloskey, N.J. Cohen, Catastrophic interference in connectionist networks: the sequential learning problem. Psychol. Learn. Motiv. 24, 109–165 (1989)CrossRefGoogle Scholar
  5. 5.
    R. Ratcliff, Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychol. Rev. 97, 285–308 (1990)CrossRefGoogle Scholar
  6. 6.
    S. Judd, On the complexity of loading shallow neural networks. J. Complex. 4, 177–192 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    E.B. Baum, A proposal for more powerful learning algorithms. Neural Comput. 1, 201–207 (1989)CrossRefGoogle Scholar
  8. 8.
    S.E. Fahlman, C. Lebiere, The cascade-correlation architecture, ed. by D.S. Touretzky. Advances in Neural Information Processing Systems (Morgan Kaufmann, San Mateo, 1990)Google Scholar
  9. 9.
    M. Frean, The upstart algorithm: a method for constructing and training feedforward neural networks. Neural Comput. 2, 198–209 (1990)CrossRefGoogle Scholar
  10. 10.
    P.T. Quinlan, Structural change and development in real and artificial networks. Neural Netw. 11, 577–599 (1998)CrossRefGoogle Scholar
  11. 11.
    P.T. Quinlan (ed.), Connectionist Models of Development (Psychology Press, New York, 2003)Google Scholar
  12. 12.
    J.F. Miller, G.M. Khan, Where is the brain inside the brain? on why artificial neural networks should be developmental. Memet. Comput. 3(3), 217–228 (2011)CrossRefGoogle Scholar
  13. 13.
    J.R. Smythies, The Dynamic Neuron (MIT Press, Cambridge, 2002)Google Scholar
  14. 14.
    F. Valverde, Rate and extent of recovery from dark rearing in the visual cortex of the mouse. Brain Res. 33, 1–11 (1971)CrossRefGoogle Scholar
  15. 15.
    J.A. Kleim, E. Lussnig, E.R. Schwartz, T.A. Comery, W.T. Greenough, Synaptogenesis and fos expression in the motor cortex of the adult rat after motor skill learning. J. Neurosci 16, 4529–4535 (1996)Google Scholar
  16. 16.
    J.A. Kleim, K. Vij, D.H. Ballard, W.T. Greenough, Learning-dependent synaptic modifications in the cerebellar cortex of the adult rat persist for at least four weeks. J. Neurosci 17, 717–721 (1997)Google Scholar
  17. 17.
    M.L. Mustroph, S. Chen, S.C. Desai, E.B. Cay, E.K. Deyoung, J.S. Rhodes. Aerobic exercise is the critical variable in an enriched environment that increases hippocampal neurogenesis and water maze learning in male C57BL/6J mice. Neuroscience (2012), Epub ahead of printGoogle Scholar
  18. 18.
    A.D. Tramontin, E. Brenowitz, Seasonal plasticity in the adult brain. Trends Neurosci. 23, 251–258 (2000)CrossRefGoogle Scholar
  19. 19.
    E.A. Maguire, D.G. Gadian, I.S. Johnsrude, C.D. Good, J. Ashburner, R.S.J. Frackowiak, C.D. Frith, Navigation-related structural change in the hippocampi of taxi drivers. PNAS 97, 4398–4403 (2000)CrossRefGoogle Scholar
  20. 20.
    S. Rose, The Making of Memory: From Molecules to Mind (Vintage, London, 2003)Google Scholar
  21. 21.
    A.S. Dekaban, D. Sadowsky, Changes in brain weights during the span of human life. Ann. Neurol. 4, 345–356 (1978)CrossRefGoogle Scholar
  22. 22.
    G.M. Khan, J.F. Miller, Evolution of cartesian genetic programs capable of learning, ed. by F. Rothlauf. Conference on Genetic and Evolutionary Computation (GECCO) (ACM, 2009) pp. 707–714Google Scholar
  23. 23.
    G.M. Khan, J.F. Miller, D.M. Halliday, Coevolution of intelligent agents using Cartesian genetic programming. Conference on Genetic and Evolutionary Computation (GECCO) (2007), pp. 269–276Google Scholar
  24. 24.
    G.M. Khan, J.F. Miller, D.M. Halliday, Breaking the synaptic dogma: Evolving a neuro-inspired developmental network, ed. by X. Li, M. Kirley, M. Zhang, D.G. Green, V. Ciesielski, H.A. Abbass, Z. Michalewicz, T. Hendtlass, K. Deb, K.C. Tan, J. Branke, Y. Shi. Simulated Evolution and Learning, 7th International Conference, SEAL 2008, Melbourne, Australia, December 7–10, 2008. Proceedings, volume 5361 of Lecture Notes in Computer Science (Springer, 2008), pp. 11–20Google Scholar
  25. 25.
    G.M. Khan, J.F. Miller, D.M. Halliday, Coevolution of neuro-developmental programs that play checkers, ed. by G. Hornby, L. Sekanina, P.C. Haddow. Evolvable Systems: From Biology to Hardware, 8th International Conference, ICES 2008, Prague, Czech Republic, September 21–24, 2008. Proceedings, volume 5216 of Lecture Notes in Computer Science (Springer, 2008), pp. 352–361Google Scholar
  26. 26.
    G.M. Khan, J.F. Miller, D.M. Halliday, Developing neural structure of two agents that play checkers using cartesian genetic programming, ed. by C. Ryan, M. Keijzer. Conference on Genetic and Evolutionary Computation (GECCO) Companion Material (ACM, 2008), pp. 2169–2174Google Scholar
  27. 27.
    G.M. Khan, J.F. Miller, D.M. Halliday, In search of intelligent genes: the cartesian genetic programming computational neuron (cgpcn), in Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2009, Trondheim, Norway, 18–21 May, 2009 (IEEE, 2009), pp. 574–581Google Scholar
  28. 28.
    G.M. Khan, J.F. Miller, D.M. Halliday, Evolution of cartesian genetic programs for development of learning neural architecture. Evol. Comput. 19(3), 469–523 (2011)CrossRefGoogle Scholar
  29. 29.
    K.O. Stanley, D.B. D’Ambrosio, J. Gauci, A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009)CrossRefGoogle Scholar
  30. 30.
    F. Gruau, Automatic definition of modular neural networks. Adapt. Behav. 3, 151–183 (1994)CrossRefGoogle Scholar
  31. 31.
    J.R. Koza, Genetic Programming: On the Programming of Computers by Natural Selection (MIT Press, Cambridge, 1992)zbMATHGoogle Scholar
  32. 32.
    J.F. Miller, An Empirical Study of the Efficiency of Learning Boolean Functions using a Cartesian Genetic Programming Approach. Conference on Genetic and Evolutionary Computation (GECCO) (Morgan Kaufmann, 1999), pp. 1135–1142Google Scholar
  33. 33.
    J.F. Miller, P. Thomson, Cartesian Genetic Programming, in Proceedings of the European Conference on Genetic Programming, vol. 1802 of LNCS (Springer, 2000), pp. 121–132Google Scholar
  34. 34.
    S. Harding, J.F. Miller, W. Banzhaf, A survey of self modifying CGP, ed. by R. Riolo, T. McConaghy, E. Vladislavleda. Genetic Programming Theory and Practice VIII, 2010 (Springer, 2010) pp. 91–107Google Scholar
  35. 35.
    S. Harding, J.F. Miller, W. Banzhaf, Self-modifying Cartesian Genetic Programming, in Proceedings of the Genetic and Evolutionary Computation Conference (2007), pp. 1021–1028Google Scholar
  36. 36.
    S. Harding, J.F. Miller, W. Banzhaf, Evolution, development and learning using self-modifying cartesian genetic programming, ed. by F. Rothlauf. Conference on Genetic and Evolutionary Computation (GECCO) (ACM, 2009), pp. 699–706Google Scholar
  37. 37.
    S. Harding, J.F. Miller, W. Banzhaf, Self modifying cartesian genetic programming: Fibonacci, squares, regression and summing, ed. by L. Vanneschi, S. Gustafson, A. Moraglio, I. De Falco, M. Ebner. Genetic Programming, 12th European Conference, EuroGP 2009, Tübingen, Germany, April 15–17, 2009, Proceedings, volume 5481 of Lecture Notes in Computer Science (Springer, 2009), pp. 133–144Google Scholar
  38. 38.
    S. Harding, J.F. Miller, W. Banzhaf, Self modifying cartesian genetic programming: Parity, in Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2009, Trondheim, Norway, 18–21 May, IEEE, 2009 (2009), pp. 285–292Google Scholar
  39. 39.
    S. Harding, J.F. Miller, W. Banzhaf, Developments in cartesian genetic programming: self-modifying cgp. Genet. Program. Evolvable Mach. 11(3–4), 397–439 (2010)CrossRefGoogle Scholar
  40. 40.
    S. Harding, J.F. Miller, W. Banzhaf, Self modifying cartesian genetic programming: finding algorithms that calculate pi and e to arbitrary precision, ed. by M. Pelikan, J. Branke. Conference on Genetic and Evolutionary Computation (GECCO) (ACM, 2010), pp. 579–586Google Scholar
  41. 41.
    M.M. Khan, G.M. Khan, J.F. Miller, Efficient representation of recurrent neural networks for Markovian/Non-Markovian non-linear control problems, ed. by A.E. Hassanien, A. Abraham, F. Marcelloni, H. Hagras, M. Antonelli, T.-P. Hong, in Proceedings of the International Conference on Intelligent Systems Design and Applications (IEEE, 2010), pp. 615–620Google Scholar
  42. 42.
    M.M. Khan, G.M. Khan, J.F. Miller, Evolution of neural networks using cartesian genetic programming, in Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2010, Barcelona, Spain, 18–23 July 2010 (IEEE, 2010)Google Scholar
  43. 43.
    M.M Khan, G.M. Khan, J.F. Miller, Evolution of optimal anns for non-linear control problems using cartesian genetic programming, ed. by H.R. Arabnia, D. de la Fuente, E.B. Kozerenko, J.A. Olivas, R. Chang, P.M. LaMonica, R.A. Liuzzi, A.M.G. Solo, in Proceedings of the 2010 International Conference on Artificial Intelligence, ICAI 2010, July 12–15, 2010, Las Vegas Nevada, USA, vol. 2 (CSREA Press, 2010), pp. 339–346Google Scholar
  44. 44.
    J.A. Walker, J.F. Miller, The automatic acquisition, evolution and reuse of modules in cartesian genetic programming. IEEE Trans. Evolut. Comput. 12(4), 397–417 (2008)CrossRefGoogle Scholar
  45. 45.
    J.F. Miller (ed.), Cartesian Genetic Programming. Natural Computing Series (Springer, Berlin, 2011)Google Scholar
  46. 46.
    I. Rechenberg, Evolutionsstrategie - Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Ph.D. thesis, Technical University of Berlin, Germany, (1971)Google Scholar
  47. 47.
    J.F. Miller, S.L. Smith, Redundancy and computational efficiency in cartesian genetic programming. IEEE Trans. Evolut. Comput. 10(2), 167–174 (2006)CrossRefGoogle Scholar
  48. 48.
    V.K. Vassilev, J.F. Miller, The Advantages of Landscape Neutrality in Digital Circuit Evolution. International Conference on Evolvable Systems, vol. 1801 of LNCS (Springer, 2000), pp. 252–263Google Scholar
  49. 49.
    T. Yu, J.F. Miller, Neutrality and the evolvability of Boolean function landscape, in Proceedings of the European Conference on Genetic Programming, vol. 2038 of LNCS (Springer, 2001), pp. 204–217Google Scholar
  50. 50.
    G.M. Khan, J.F Miller, Solving mazes using an artificial developmental neuron, in Proceedings of the Conference on Artificial Life (ALIFE) XII (MIT Press, 2010), pp. 241–248Google Scholar
  51. 51.
    S. Harding, J.F. Miller, W. Banzhaf, SMCGP2: Self-modifying Cartesian Genetic Programming in Two Dimensions. Conference on Genetic and Evolutionary Computation (GECCO) (ACM, 2011), pp. 1491–1498Google Scholar
  52. 52.
    W. Gerstner, W.M. Kistler, Spiking Neuron Models (Cambridge University Press, Cambridge, 2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Department of ElectronicsUniversity of YorkYorkUK

Personalised recommendations