Advertisement

Vygotsky Meets Backpropagation

Artificial Neural Models and the Development of Higher Forms of Thought
  • Ilkka TuomiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10947)

Abstract

In this paper we revisit Vygotsky’s developmental model of concept formation, and use it to discuss learning in artificial neural networks. We study learning in neural networks from a learning science point of view, asking whether it is possible to construct systems that have developmental patterns that align with empirical studies on concept formation. We put the state-of-the-art Inception-v3 image recognition architecture in an experimental setting that highlights differences and similarities in algorithmic and human cognitive processes.

The Vygotskian model of cognitive development reveals important limitations in currently popular neural algorithms, and puts neural AI in the context of post-behavioristic science of learning. At the same time, the Vygotskian model of development of thought suggests new architectural principles for developing AI, machine learning, and systems that support human learning. In this context we can ask what would it take for machines to learn, and what could they learn from research on learning.

Keywords

Development of cognition Inception Neural AI Conceptual thinking Abstraction Generalization Categorization 

References

  1. 1.
    Anderson, J.A., Rosenfeld, E. (eds.): Neurocomputing: Foundations for Research. The MIT Press, Cambridge (1988)Google Scholar
  2. 2.
    Bergson, H.: Creative Evolution (1st edn. 1907). University Press of America, Lanham (1983)Google Scholar
  3. 3.
    Carpenter, G., Grossberg, S.: A massively parallel architecture for self-organizing neural pattern recognition machine. Comput. Vis. Graph. Image Process. 37, 54–115 (1987)CrossRefGoogle Scholar
  4. 4.
    Davydov, V.V.: Types of Generalization in Instruction: Logical and Psychological Problems in the Structuring of School Curricula. National Council of Teachers of Mathematics, Reston (1990)Google Scholar
  5. 5.
    Hagan, M.T., Demuth, H.B., Beale, M.H., Jess, O.D.: Neural Network Design, 2nd edn. Martin Hagan, Boston (2014)Google Scholar
  6. 6.
    Hanfmann, E., Kasanin, J.: Conceptual Thinking in Schizophrenia. NMDM, New York (1942)CrossRefGoogle Scholar
  7. 7.
    Kohonen, T.: The self-organizing map. Neurocomputing 21(1), 1–6 (1998).  https://doi.org/10.1016/S0925-2312(98)00030-7MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Kozulin, A.: Vygotsky’s Psychology: A Biography of Ideas. Harvard University Press, Cambridge (1990)Google Scholar
  9. 9.
    Lakoff, G.: Women, Fire, and Dangerous Things: What Categories Reveal About the Mind. University of Chicago Press, Chicago (1987)CrossRefGoogle Scholar
  10. 10.
    Lane, H.C., McCalla, G., Looi, C.K., Bull, S.: Preface to the IJAIED 25th anniversary issue, part 2. Int. J. Artif. Intell. Educ. 26(2), 539–543 (2016).  https://doi.org/10.1007/s40593-016-0109-9CrossRefGoogle Scholar
  11. 11.
    Louie, A.H.: The Reflection of Life: Functional Entailment and Imminence in Relational Biology. Springer, New York (2013).  https://doi.org/10.1007/978-1-4614-6928-5CrossRefzbMATHGoogle Scholar
  12. 12.
    Luria, A., Vygotsky, L.: Ape, Primitive Man, and Child: Essays in the History of Behavior. Harvester Wheatsheaf, Hemel Hempstead (1992)Google Scholar
  13. 13.
    Mikolov, T., Karafiát, M., Burget, L., Černocký, J., Khudanpur, S.: Recurrent neural network based language model. In: Kobayashi, T., Hirose, K., Satoshi, N. (eds.) INTERSPEECH-2010. pp. 1045–1048. Makuhari, Chiba (2010). http://www.isca-speech-org/archive/interspeech_2010
  14. 14.
    Morrison, D.M., Miller, K.B.: Teaching and learning in the pleistocene: a biocultural account of human pedagogy and its implications for AIED. Int. J. Artif. Intell. Educ., 1–31 (2017).  https://doi.org/10.1007/s40593-017-0153-0
  15. 15.
    Rashevsky, N.: Mathematical Biophysics: Physico-Mathematical Foundations of Biology, 3rd edn. Dover, New York (1960)Google Scholar
  16. 16.
    Rosen, R.: Fundamentals of Measurement and Representation of Natural Systems. North-Holland, New York (1978)Google Scholar
  17. 17.
    Rosen, R.: Life Itself: A Comprehensible Inquiry into the Nature, Origin and Fabrication of Life. Columbia University Press, New York (1991)Google Scholar
  18. 18.
    Sakharov, L.: Methods for investigating concepts. In: van der Veer, R., Valsiner, J. (eds.) The Vygotsky Reader, pp. 73–98. Blackwell, Oxford (1994)Google Scholar
  19. 19.
    Shimizu, H., Yamaguchi, Y.: Synergetic computer and holonics: information dynamics of a semantic computer. Phys. Scr. 36(6), 970–985 (1987)CrossRefGoogle Scholar
  20. 20.
    Short, T.L.: Peirce’s Theory of Signs. Cambridge University Press, Cambridge (2009)Google Scholar
  21. 21.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016).  https://doi.org/10.1109/CVPR.2016.308
  22. 22.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions (2014). arXiv:1409.4842
  23. 23.
    Tuomi, I.: Vygotsky in a TeamRoom: an exploratory study on collective concept formation in electronic environments. In: Nunamaker, J. (ed.) Proceedings of the 31st Annual Hawaii International Conference on System Sciences, vol. 1, pp. 68–75. IEEE Computer Society Press, Los Alamitos (1998).  https://doi.org/10.1109/HICSS.1998.653085
  24. 24.
    Tuomi, I.: Corporate Knowledge: Theory and Practice of Intelligent Organizations. Metaxis, Helsinki (1999)Google Scholar
  25. 25.
    Tuomi, I.: Data is more than knowledge: implications of the reversed knowledge hierarchy to knowledge management and organizational memory. J. Manag. Inf. Syst. 6(3), 103–117 (2000).  https://doi.org/10.1080/07421222.1999.11518258CrossRefGoogle Scholar
  26. 26.
    Tuomi, I.: Ontological expansion. In: Poli, R. (ed.) Handbook of Anticipation, pp. 1–35. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-31737-3_4-1CrossRefGoogle Scholar
  27. 27.
    van der Veer, R., Valsiner, J.: Understanding Vygotsky: A Quest for Synthesis. Blackwell Publishers, Cambridge (1994)Google Scholar
  28. 28.
    Vygotsky, L.: Mind in Society: The Development of Higher Psychological Processes. Harvard University Press, Cambridge (1978)Google Scholar
  29. 29.
    Vygotsky, L.: Thought and Language. The MIT Press, Cambridge (1986)Google Scholar
  30. 30.
    Wertsch, J.: Vygotsky and the Social Formation of Mind. Harvard University Press, Cambridge (1985)Google Scholar
  31. 31.
    Zueva, E.Y., Zuev, K.B.: The concept of dominance by A.A. Ukhtomsky and anticipation. In: Nadin, M. (ed.) Anticipation: Learning from the Past - The Russian/Soviet Contributions to the Science of Anticipation, pp. 13–35. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-19446-2_2CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Meaning ProcessingHelsinkiFinland

Personalised recommendations