Advertisement

Supervised Neural Network Learning with an Environment Adapted Supervision Based on Motivation Learning Factors

  • Maciej Janowski
  • Adrian HorzykEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10841)

Abstract

This paper introduces an innovative approach for supervised learning systems in cases when we do not have initially defined training data sets, but we need to develop them gradually during training process on the basis of the motivation factors that come from the given environment. We suppose to gradually develop and update knowledge about the environment and use it for supervision of training MLP. In the beginning, the gradually gained knowledge does not have to be correct, but it allows to adapt a neural network still better and more efficiently in time. It is illustrated on the problem of acquiring the ability to return to the starting position optimally by a virtual robot from anywhere in an initially unknown and gradually explored maze. The proposed approach focuses on the attempt to reflect human cognitive abilities and motivation factors in an introduced model using artificial neural networks. This article presents a new approach in which the decision-making method arises from the supervised learning process controlled by the knowledge gained during maze exploration. This paper presents a model of maze exploration and knowledge-based adaptation of the neural network. The experimental results of the classical supervised learning approach and the proposed modified approach will be compared to demonstrate significant improvements.

Keywords

Neural network Motivated learning Supervised learning Environment adapted supervision Knowledge-based learning Knowledge development Brain-inspired computations Cognitive systems 

References

  1. 1.
    Janowski, M.: Use of a neural network to move a robot back to the starting position in a maze using supervised learning. Engineering dissertation at the AGH University of Science and Technology in Krakow supervised and promoted by A. Horzyk (2018)Google Scholar
  2. 2.
    Tadeusiewicz, R., Horzyk, A.: Man-machine interaction improvement by means of automatic human personality identification. In: Saeed, K., Snášel, V. (eds.) CISIM 2014. LNCS, vol. 8838, pp. 278–289. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-662-45237-0_27CrossRefGoogle Scholar
  3. 3.
    Jiang, P., Zhang, Y., Fu, W., Liu, H., Su, X.: Indoor mobile localization based on Wi-Fi fingerprint’s important access point. Int. J. Distrib. Sens. Netw. 11, 429104 (2015)CrossRefGoogle Scholar
  4. 4.
    Nunez, M.J.: Water maze experiment. J. Vis. Exp. JoVE 19, 897 (2008).  https://doi.org/10.3791/897CrossRefGoogle Scholar
  5. 5.
    Brandeis, R., Brandys, Y., Yehuda, S.: The use of the Morris water maze in the study of memory and learning. Int. J. Neurosci. 48(1–2), 29–69 (1989)CrossRefGoogle Scholar
  6. 6.
    Horzyk, A., Starzyk, J.A., Graham, J.: Integration of semantic and episodic memories. IEEE Trans. Neural Netw. Learn. Syst. 28(12), 3084–3095 (2017).  https://doi.org/10.1109/TNNLS.2017.2728203MathSciNetCrossRefGoogle Scholar
  7. 7.
    Eichenbaum, H.: A cortical-hippocampal system for declarative memory. Nat. Rev. Neurosci. 1, 41–50 (2000)CrossRefGoogle Scholar
  8. 8.
    Kandel, E.R., Schwartz, J.H., Jessell, T.M., Siegelbaum, S.A., Hudspeth, A.J. (eds.): Principles of Neural Science. McGraw-Hill, New York (2013)Google Scholar
  9. 9.
    Heinrich, B., Bugnyar, T.: Just how smart are ravens? Sci. Am. 296, 64–71 (2007)CrossRefGoogle Scholar
  10. 10.
    Fiorito, G., Scotto, P.: Observational learning in Octopus vulgaris. Science 256, 545–547 (1992)CrossRefGoogle Scholar
  11. 11.
    Loukola, O.J., Perry, C.J., Coscos, L., Chittka, L.: Bumblebees show cognitive flexibility by improving on an observed complex behavior. Science 355, 833 (2017)CrossRefGoogle Scholar
  12. 12.
    Rutkowski, L.: Techniques and methods of artificial intelligence. PWN (2012)Google Scholar
  13. 13.
    Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015). http://neuralnetworksanddeeplearning.com/
  14. 14.
    Duch, W.: Brain-inspired conscious computing architecture. J. Mind Behav. 26, 1–22 (2005)Google Scholar
  15. 15.
    Berlyne, D.E.: Novelty and curiosity as determinants of exploratory behavior. Br. J. Psychol. 41, 68–80 (1950)Google Scholar
  16. 16.
    Dember, W.N.: Response by the rat to environmental change. J. Comp. Physiol. Psychol. 49, 93 (1956)CrossRefGoogle Scholar
  17. 17.
    Hughes, R.N.: Behaviour of male and female rats with free choice of two environments differing in novelty. Anim. Behav. 16, 92–96 (1968)CrossRefGoogle Scholar
  18. 18.
    Berlyne, D.E.: Conflict, Arousal, and Curiosity. McGraw Hill, New York (1960)CrossRefGoogle Scholar
  19. 19.
    Larose, D.T.: Discovering knowledge from data. Introduction to Data Mining. PWN, Warsaw (2006)Google Scholar
  20. 20.
    Day, H.I.: Curiosity and the interested explorer. Nonprofit Manage. Leadersh. 21, 19–22 (1982).  https://doi.org/10.1002/pfi.4170210410CrossRefGoogle Scholar
  21. 21.
    Hecht-Nielsen, R.: III.3 - Theory of the backpropagation neural network. In: Wechsler, H. (ed.) Neural Networks for Perception, pp. 65–93. Academic Press (1992)Google Scholar
  22. 22.
    Hertz, J., Krogh, A., Palmer, R.G.: Santa Fe Institute studies in the sciences of complexity: lecture notes, vol. 1 and computation and neural systems series. In: Introduction to the Theory of Neural Computation. Addison-Wesley/Addison Wesley Longman, Reading (1991)Google Scholar
  23. 23.
    Ke, Q., Oommen, B.J.: Logistic neural networks: their chaotic and pattern recognition properties. Neurocomputing 125, 184–194 (2014)CrossRefGoogle Scholar
  24. 24.
    Davis, L.D.: Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York (1991)Google Scholar
  25. 25.
    Holland, J.: Adaptation in Natural and Artificial Systems, pp. 89–120. University of Michigan Press, Ann Arbor (1975)Google Scholar
  26. 26.
    Tadeusiewicz, R.: Introduction to Intelligent Systems, Fault Diagnosis. Models, Artificial Intelligence, Applications. CRC Press, Boca Raton (2011)Google Scholar
  27. 27.
    Tadeusiewicz, R.: New trends in neurocybernetics. Comput. Methods Mater. Sci. 10(1), 17 (2010)Google Scholar
  28. 28.
    Horzyk, A.: How does generalization and creativity come into being in neural associative systems and how does it form human-like knowledge? Neurocomputing 144, 238–257 (2014)CrossRefGoogle Scholar
  29. 29.
    Horzyk, A.: Artificial associative systems and associative artificial intelligence, pp. 1–276. EXIT, Warsaw (2013)Google Scholar
  30. 30.
    Horzyk, A.: Human-like knowledge engineering, generalization, and creativity in artificial neural associative systems. In: Skulimowski, A.M.J., Kacprzyk, J. (eds.) Knowledge, Information and Creativity Support Systems: Recent Trends, Advances and Solutions. AISC, vol. 364, pp. 39–51. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-19090-7_4CrossRefGoogle Scholar
  31. 31.
    Kalat, J.W.: Biological Grounds of Psychology. PWN, Warsaw (2006)Google Scholar
  32. 32.
    Starzyk, J.A.: Motivated learning for computational intelligence. In: Computational Modeling and Simulation of Intellect: Current State and Future Perspectives. IGI Publishing, pp. 265–292 (2011). Red. B. IgelnikGoogle Scholar
  33. 33.
    Starzyk, J.A., Graham, J., Horzyk, A.: Trust in motivated learning agents. In: IEEE Symposium Series on Computational Intelligence, Greece, Athens, ISBN 978-1-5090-4239-5. IEEE Xplore (2016).  https://doi.org/10.1109/SSCI.2016.7850027

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.AGH University of Science and TechnologyKrakowPoland

Personalised recommendations