DEVELOPMENTAL PLASTICITY IN CARTESIAN GENETIC PROGRAMMING BASED NEURAL NETWORKS

Maryam Mahsal Khan, Gul Muhammad Khan, Julian F. Miller

2011

Abstract

This work presents a method for exploiting developmental plasticity in Artificial Neural Networks using Cartesian Genetic Programming. This is inspired by developmental plasticity that exists in the biological brain allowing it to adapt to a changing environment. The network architecture used is that of a static Cartesian Genetic Programming ANN, which has recently been introduced. The network is plastic in terms of its dynamic architecture, connectivity, weights and functionality that can change in response to the environmental signals. The dynamic capabilities of the algorithm are tested on a standard benchmark linear/non-linear control problems (i.e. pole-balancing).

References

  1. Ans, B., Rousset, S., French, R. M., and Musca, S. (2002). Preventing catastrophic interference in multiple-sequence learning using coupled reverberating elman networks. In Proc. 24th, Annual conf. of cognitive science society, pages 71-76.
  2. Baxter, J. (1992). The evolution of learning algorithms for artificial neural networks. D.Green & T.Bossomaier, Complex Systems, pages 313 - 326.
  3. Cangelosi, A., Nolfi, S., and Parisi, D. (1994). Cell division and migration in a 'genotype' for neural networks. Network-Computation in Neural Systems, 5:497-515.
  4. Clune, J., Beckmann, B. E., Ofria, C., and Pennock, R. T. (2008). Evolving coordinated quadruped gaits with the hyperneat generative encoding. Proc. IEEE CEC'2008, pages 2764-2771.
  5. Dalaert, F. and Beer, R. (1994). Towards an evolvable model of development for autonomous agent synthesis. In Brooks, R. and Maes, P. eds. Proc. 4rth Conf. on Artificial Life. MIT Press.
  6. Floreano, D. and Urzelai, J. (2000). Evolutionary robots with online self-organization and behavioral fitness. Neural Networks, 13:431 - 443.
  7. French, R. M. (1994). Catastrophic forgetting in connectionist networks: Causes, consequences and solutions. In Trends in Cognitive Sciences, pages 128-135.
  8. Gomez, F., Schmidhuber, J., and Miikkulainen, R. (2008). Accelerated neural evolution through cooperatively coevolved synapses. J. Mach. Learn. Res., 9:937-965.
  9. Gomez, F. J. and Miikkulainen, R. (1999). Solving nonmarkovian control tasks with neuroevolution. In Proc. Int. joint Conf. on Artificial intelligence, pages 1356- 1361. Morgan Kaufmann Publishers Inc.
  10. Gruau, F. (1994). Automatic definition of modular neural networks. Adaptive Behaviour, 3:151-183.
  11. Gruau, F., Whitley, D., and Pyeatt, L. (1996). A comparison between cellular encoding and direct encoding for genetic neural network. In Genetic Programming 1996:Proceeding of the First Annual conference, pages 81-89 MIT Press.
  12. Harding, S., Miller, J. F., and Benzhaf, W. (2010). Developments in cartesian genetic programming:selfmodifying cgp. GPEM, 11(2):397-439.
  13. Hussain, T. and Browse, R. (2000). Evolving neural networks using attribute grammars. IEEE Symp. Combinations of Evolutionary Computation and Neural Networks, 2000, pages 37 - 42.
  14. Jacob, C. and Rehder, J. (1993). Evolution of neural net architectures by a hierarchical grammar-based genetic system. In Proc. ICANNGA93, pages 72-79. Springer-Verlag.
  15. Kandel, E. R., Schwartz, J. H., and Jessell (2002). Principles of Neural Science, 4rth Edition. McGraw-Hill.
  16. Khan, G., Miller, J., and Halliday, D. (2007). Coevolution of intelligent agents using cartesian genetic programming. In Proc. GECCO'2007, pages 269 - 276.
  17. Khan, M., Khan, G., and F. Miller, J. (2010a). Evolution of optimal anns for non-linear control problems using cartesian genetic programming. In Proc. IEEE. ICAI'2010.
  18. Khan, M., Khan, G., and Miller, J. (2010b). Efficient representation of recurrent neural networks for markovian/non-markovian non-linear control problems. In Proc. ISDA'2010, pages 615-620.
  19. Kitano, H. (1990). Designing neural networks using genetic algorithm with graph generation system. Complex Systems, 4:461-476.
  20. McCloskey, M. and Cohen, N. (1989). Catastrophic interference in connectionist networks: The sequential learning problem. The Psychology of Learning and Motivation, 24:109-165.
  21. Miller, J. and Smith, S. (2006). Redundancy and computation efficiency in cartesian genetic programming. IEEE Trans. Evol. Comp., 10:167-174.
  22. Miller, J. F. and Thomson, P. (2000). Cartesian genetic programming. In Proc. EuroGP'2000, volume 1802, pages 121-132.
  23. Moriarty, D. (1997). Symbiotic Evolution of Neural Networks in Sequential Decision Tasks. PhD thesis, University of Texas at Austin.
  24. Nicholas F.McPhee, Ellery Crane, S. E. and Poli, R. (2009). Developmental plasticity in linear genetic programming. Proc. GECCO'2009, pages 1019-1026.
  25. Nolfi, S., Miglino, O., and Parisi, D. (1994). Phenotypic plasticity in evolving neural networks. In Proc. Int. Conf. from perception to action. IEEE Press.
  26. Ratcliff, R. (1990). Connectionist models of recognition and memory:constraints imposed by learning and forgetting functions. Psychological Review, 97:205-308.
  27. Risi, S., Hughes, C. E., and Stanley, K. O. (2010). Evolving plastic neural networks with novelty search. Adaptive Behavior.
  28. Rivero, D., Rabual, J., Dorado, J., and Pazos, A. (2007). Automatic design of anns by means of gp for data mining tasks: Iris flower classification problem. Adaptive and Natural Computing Algorithms, 4431:276-285.
  29. Roggen, D., Federici, D., and Floreano, D. (2007). Evolutionary morphogenesis for multi-cellular systems. GPEM, 8:61-96.
  30. Rust, A., Adams, R., and H., B. (2000). Evolutionary neural topiary: Growing and sculpting artificial neurons to order. In Proc. ALife VII, pages 146-150. MIT Press.
  31. Sharkey, N. and Sharkey, A. (1995). An analysis of catastrophic interference. Connection Science, 7(3-4):301- 330(30).
  32. Sims, K. (1994). Evolving 3d morphology and behavior by competition. In Artificial life 4 proceedings, pages 28-39. MIT Press.
  33. Stanley, K. O., D'Ambrosio, D. B., and Gauci, J. (2009). A hypercube-based encoding for evolving large-scale neural networks. Artif. Life, 15:185-212.
  34. Stanley, K. O. and Miikkulainen, R. (2002). Evolving neural network through augmenting topologies. Evolutionary Computation, 10(2):99-127.
  35. Wieland, A. P. (1991). Evolving neural network controllers for unstable systems. In Proc. Int. Joint Conf. Neural Networks, pages 667-673.
Download


Paper Citation


in Harvard Style

Mahsal Khan M., Muhammad Khan G. and F. Miller J. (2011). DEVELOPMENTAL PLASTICITY IN CARTESIAN GENETIC PROGRAMMING BASED NEURAL NETWORKS . In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ANNIIP, (ICINCO 2011) ISBN 978-989-8425-74-4, pages 449-458. DOI: 10.5220/0003615204490458


in Bibtex Style

@conference{anniip11,
author={Maryam Mahsal Khan and Gul Muhammad Khan and Julian F. Miller},
title={DEVELOPMENTAL PLASTICITY IN CARTESIAN GENETIC PROGRAMMING BASED NEURAL NETWORKS},
booktitle={Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ANNIIP, (ICINCO 2011)},
year={2011},
pages={449-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003615204490458},
isbn={978-989-8425-74-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ANNIIP, (ICINCO 2011)
TI - DEVELOPMENTAL PLASTICITY IN CARTESIAN GENETIC PROGRAMMING BASED NEURAL NETWORKS
SN - 978-989-8425-74-4
AU - Mahsal Khan M.
AU - Muhammad Khan G.
AU - F. Miller J.
PY - 2011
SP - 449
EP - 458
DO - 10.5220/0003615204490458