Advertisement

Co-evolutionary Multi-task Learning for Modular Pattern Classification

  • Rohitash Chandra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10639)

Abstract

Modularity in the learning process is a means by which effective decision making can be maintained when some of the input features are missing. In this paper, co-evolutionary multi-task learning algorithm is used for pattern classification which is robust to situations when some input features are unavailable during the deployment stage of decision support or control systems. The main feature of the algorithm is the ability to make decisions with some degree of error given misinformation. The results show that the method produces results comparable to non-modular methods while having modular features for dynamic and robust pattern classification.

Keywords

Cooperative coevolution Neuroevolution Multi-task learning Modular pattern classification 

References

  1. 1.
    Angeline, P., Saunders, G., Pollack, J.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. Neural Netw. 5(1), 54–65 (1994)CrossRefGoogle Scholar
  2. 2.
    Caruana, R.: Multitask learning. In: Thrun, S., Pratt, L. (eds.) Learning to Learn, pp. 95–133. Springer, Boston (1998)CrossRefGoogle Scholar
  3. 3.
    Chandra, R., Frean, M., Zhang, M.: On the issue of separability for problem decomposition in cooperative neuro-evolution. Neurocomputing 87, 33–40 (2012)CrossRefGoogle Scholar
  4. 4.
    Chandra, R., Ong, Y.S., Goh, C.K.: Co-evolutionary multi-task learning for dynamic time series prediction. CoRR abs/1703.01887 (2017). http://arxiv.org/abs/1703.01887
  5. 5.
    Chandra, R., Ong, Y.S., Goh, C.K.: Co-evolutionary multi-task learning with predictive recurrence for multi-step chaotic time series prediction. Neurocomputing 243, 21–34 (2017)CrossRefGoogle Scholar
  6. 6.
    Chandra, R., Zhang, M.: Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction. Neurocomputing 186, 116–123 (2012)CrossRefGoogle Scholar
  7. 7.
    Clune, J., Mouret, J.B., Lipson, H.: The evolutionary origins of modularity. Proc. R. Soc. Lond. B Biol. Sci. 280(1755), 20122863 (2013). doi: 10.1098/rspb.2012.2863 CrossRefGoogle Scholar
  8. 8.
    Dash, M., Liu, H.: Feature selection for classification. Intell. Data Anal. 1(3), 131–156 (1997)CrossRefGoogle Scholar
  9. 9.
    Ellefsen, K.O., Mouret, J.B., Clune, J.: Neural modularity helps organisms evolve to learn new skills without forgetting old skills. PLoS Comput. Biol. 11(4), 1–24 (2015)CrossRefGoogle Scholar
  10. 10.
    Geschwind, N., Behan, P.: Left-handedness: association with immune disease, migraine, and developmental learning disorder. Proc. Natl. Acad. Sci. 79(16), 5097–5100 (1982)CrossRefGoogle Scholar
  11. 11.
    Hansen, N., Müller, S.D., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evol. Comput. 11(1), 1–18 (2003)CrossRefGoogle Scholar
  12. 12.
    Happel, B.L., Murre, J.M.: Design and evolution of modular neural network architectures. Neural Netw. 7(6–7), 985–1004 (1994)CrossRefGoogle Scholar
  13. 13.
    Johnson, M.K.: A multiple-entry, modular memory system. Psychol. Learn. Motiv. 17, 81–123 (1983). Academic PressCrossRefGoogle Scholar
  14. 14.
    Lee, M.H., Meng, Q., Chao, F.: Developmental learning for autonomous robots. Robot. Auton. Syst. 55(9), 750–759 (2007)CrossRefGoogle Scholar
  15. 15.
    Lichman, M.: UCI Machine Learning Repository. School of Information and Computer Science, University of California, Irvine (2013). http://archive.ics.uci.edu/ml
  16. 16.
    Meunier, D., Lambiotte, R., Bullmore, E.T.: Modular and hierarchically modular organization of brain networks. Front. Neurosci. 4, 200 (2010). doi: 10.3389/fnins.2010.00200 CrossRefGoogle Scholar
  17. 17.
    Miller, W.T.: Real-time application of neural networks for sensor-based control of robots with vision. IEEE Trans. Syst. Man Cybern. 19(4), 825–831 (1989)CrossRefGoogle Scholar
  18. 18.
    Potter, M.A., Jong, K.A.: A cooperative coevolutionary approach to function optimization. In: Davidor, Y., Schwefel, H.-P., Männer, R. (eds.) PPSN 1994. LNCS, vol. 866, pp. 249–257. Springer, Heidelberg (1994). doi: 10.1007/3-540-58484-6_269 CrossRefGoogle Scholar
  19. 19.
    Potter, M.A., De Jong, K.A.: Cooperative coevolution: an architecture for evolving coadapted subcomponents. Evol. Comput. 8(1), 1–29 (2000)CrossRefGoogle Scholar
  20. 20.
    Saeys, Y., Inza, I., Larrañaga, P.: A review of feature selection techniques in bioinformatics. Bioinformatics 23(19), 2507–2517 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Centre for Translational Data ScienceThe University of SydneySydneyAustralia

Personalised recommendations