Advertisement

No Two Brains Are Alike: Cloning a Hyperdimensional Associative Memory Using Cellular Automata Computations

  • Denis Kleyko
  • Evgeny Osipov
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 636)

Abstract

This paper looks beyond of the current focus of research on biologically inspired cognitive systems and considers the problem of replication of its learned functionality. The considered challenge is to replicate the learned knowledge such that uniqueness of the internal symbolic representations is guaranteed. This article takes a neurological argument “no two brains are alike” and suggests an architecture for mapping a content of the trained associative memory built using principles of hyperdimensional computing and Vector Symbolic Architectures into a new and orthogonal basis of atomic symbols. This is done with the help of computations on cellular automata. The results of this article open a way towards a secure usage of cognitive architectures in a variety of practical application domains.

Notes

Acknowledgements

This study is supported in part by the Swedish Research Council (grant no. 2015-04677). The authors thank Ozgur Yilmaz for fruitful discussions during BICA2016 on the usage of cellular automata in the scope of hyperdimensional computing, which inspired the current work and Niklas Karvonen for general discussions on cellular automata.

References

  1. 1.
    Gayler, R.W.: Vector symbolic architectures answer Jackendoff’s challenges for cognitive neuroscience. In: Proceedings of the Joint International Conference on Cognitive Science. ICCS/ASCS, pp. 133–138 (2003)Google Scholar
  2. 2.
    Emruli, B., Sandin, F.: Analogical mapping with sparse distributed memory: a simple model that learns to generalize from examples. Cogn. Comput. 6(1), 74–88 (2014)CrossRefGoogle Scholar
  3. 3.
    Kleyko, D., Osipov, E., Papakonstantinou, N., Vyatkin, V., Mousavi, A.: Fault detection in the hyperspace: towards intelligent automation systems. In: IEEE International Conference on Industrial Informatics, INDIN, pp. 1–6 (2015)Google Scholar
  4. 4.
    Rahimi, A., Benatti, S., Kanerva, P., Benini, L., Rabaey, J.M.: Hyperdimensional biosignal processing: a case study for emg-based hand gesture recognition. In: 2016 IEEE International Conference on Rebooting Computing (ICRC), pp. 1–8 (2016)Google Scholar
  5. 5.
    Kleyko, D., Osipov, E., Gayler, R.W.: Recognizing permuted words with vector symbolic architectures: a cambridge test for machines. Procedia Comput. Sci. 88, 169–175 (2016)CrossRefGoogle Scholar
  6. 6.
    Levy, S.D., Gayler, R.: Vector symbolic architectures: a new building material for artificial general intelligence. In: Proceedings of the 2008 Conference on Artificial General Intelligence 2008, pp. 414–418 (2008)Google Scholar
  7. 7.
    Rachkovskij, D.A., Kussul, E.M., Baidyk, T.N.: Building a world model with structure-sensitive sparse binary distributed representations. Biol. Inspir. Cogn. Archit. 3, 64–86 (2013)Google Scholar
  8. 8.
    Kleyko, D., Osipov, E., Gayler, R.W., Khan, A.I., Dyer, A.G.: Imitation of honey bees’ concept learning processes using vector symbolic architectures. Biol. Inspir. Cogn. Archit. 14, 57–72 (2015)Google Scholar
  9. 9.
    Kleyko, D., Osipov, E., Bjork, M., Toresson, H., Oberg, A.: Fly-the-bee: a game imitating concept learning in bees. Procedia Comput. Sci. 71, 25–30 (2015)CrossRefGoogle Scholar
  10. 10.
    Eliasmith, C.: How to Build a Brain. Oxford University Press, Oxford (2013)CrossRefGoogle Scholar
  11. 11.
    Kanerva, P.: Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn. Comput. 1(2), 139–159 (2009)CrossRefGoogle Scholar
  12. 12.
    Gallant, S.I., Okaywe, T.W.: Representing objects, relations, and sequences. Neural Comput. 25(8), 2038–2078 (2013)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Plate, T.A.: Holographic reduced representations. IEEE Trans. Neural Netw. 6(3), 623–641 (1995)CrossRefGoogle Scholar
  14. 14.
    Kleyko, D., Osipov, E., Rachkovskij, D.A.: Modification of holographic graph neuron using sparse distributed representations. Procedia Comput. Sci. 88, 39–45 (2016)CrossRefGoogle Scholar
  15. 15.
    Aerts, D., Czachor, M., De Moor, B.: Geometric analogue of holographic reduced representation. J. Math. Psychol. 53, 389–398 (2009)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Rachkovskij, D.A.: Representation and processing of structures with binary sparse distributed codes. IEEE Trans. Knowl. Data Eng. 3(2), 261–276 (2001)CrossRefGoogle Scholar
  17. 17.
    Kanerva, P.: Fully distributed representation. In: Real World Computing Symposium, pp. 358–365 (1997)Google Scholar
  18. 18.
    Kanerva, P.: Sparse Distributed Memory. The MIT Press, Cambridge (1988)zbMATHGoogle Scholar
  19. 19.
    Kleyko, D., Osipov, E., Senior, A., Khan, A.I., Sekercioglu, Y.A.: Holographic graph neuron: a bioinspired architecture for pattern processing. IEEE Trans. Neural Netw. Learn. Syst. 28(6), 1250–1263 (2017)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Kanerva, P.: What we mean when we say “What’s the Dollar of Mexico?”. In: AAAI Fall Symposium. Quantum Informatics for Cognitive, Social, and Semantic Processes, pp. 2–6 (2010)Google Scholar
  21. 21.
    Lieto, A., Lebiere, C., Oltramari, A.: The knowledge level in cognitive architectures: current limitations and possible developments. In: Cognitive Systems Research, pp. 1–17 (2017)Google Scholar
  22. 22.
    Lieto, A., Chella, A., Frixione, M.: Conceptual spaces for cognitive architectures. Biol. Inspir. Cogn. Archit. 19, 1–9 (2017)Google Scholar
  23. 23.
    Wolfram, S.: A New Kind of Science. Wolfram Media Inc., Champaign (2002)zbMATHGoogle Scholar
  24. 24.
    Yilmaz, O.: Machine learning using cellular automata based feature expansion and reservoir computing. J. Cell. Automata 10(5–6), 435–472 (2015)MathSciNetzbMATHGoogle Scholar
  25. 25.
    Yilmaz, O.: Symbolic computation using cellular automata-based hyperdimensional computing. Neural Comput. 27(12), 2661–2692 (2015)CrossRefGoogle Scholar
  26. 26.
    Nichele, S., Molund, A.: Deep reservoir computing using cellular automata, pp. 1–9 (2017). arXiv:1703.02806
  27. 27.
    Kleyko, D., Khan, S., Osipov, E., Yong, S.P.: Modality classification of medical images with distributed representations based on cellular automata reservoir computing. In: IEEE International Symposium on Biomedical, Imaging, pp. 1–4 (2017)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Luleå University of TechnologyLuleåSweden

Personalised recommendations