[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Log in

Brain-like Computing Based on Distributed Representations and Neurodynamics

  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

A key to overcoming the limitations of classical artificial intelligence and to deal well with enormous amounts of information might be brain-like computing in which distributed representations of information are processed by dynamical systems without using symbols. We present a method for such computing. We constructed an inference system using a nonmonotone neural network, which is a kind of recurrent neural network with continuous-time dynamics. This system deduces a conclusion according to state transitions of the network in which knowledge is embedded as trajectory attractors. It has the powerful ability of analogical reasoning without special treatment for exceptional knowledge. We also propose a method of linking different neurodynamical systems and show that two mutually interacting systems can process complex spatiotemporal patterns.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Harnad, S.,“The symbol grounding problem,” Physica D, 42, pp. 335–346, 1990.

    Article  Google Scholar 

  2. McCarty, J. and Hayes, P. J., “Some philosophical problems from the standpoint of artificial intelligence,” Machine Intelligence, 4, pp. 463–502, 1969.

    Google Scholar 

  3. Sandewall, E.,“An approach to the frame problem and its implementation,” Machine Intelligence, 7, pp. 195–204, 1972.

    MATH  Google Scholar 

  4. Morita, M. and Suemitsu, A., “Computational modeling of pair-association memory in inferior temporal cortex,” Cogn. Brain Res., 13, pp. 169–178, 2002.

    Article  Google Scholar 

  5. Suemitsu, A., Morokami, S., Murata, K. and Morita, M., “Computational examination on the dynamics of recall activity in the inferior temporal cortex,” in Proc. of the 2002 IJCNN, pp. 136–141, 2002.

  6. Suemitsu, A. and Morita, M., “A neural network model of context-dependent neuronal activity in the inferotemporal cortex,” in Proc. of the 2006 IJCNN, pp. 685–690, 2006.

  7. Rumelhart, D. E., McClelland, J. L. and the PDP Research Group, Parallel distributed processing: Explorations in the microstructure of cognition volume 1: Foundations, MIT Press, Cambridge, 1986.

  8. Blelloch, G. E., “CIS: A massively concurrent rule-based system,” in Proc. of the AAAI-86, pp. 735–741, 1986.

  9. D'Avila Garcez, Artur S., Lamb, Luis C. and Gabbay, Dov M., Neural-symbolic cognitive reasoning, Springer-Verlag, Berlin, 2009.

  10. Touretzky, D. S. and Hinton, G. E., “Symbols among the neurons: details of a connectionist inference architecture,” in Proc. of the IJCAI-85, pp. 238–243, 1985.

  11. Touretzky, D. S. and Hinton G. E., “A distributed connectionist production system,” Cogn. Sci., 12, pp. 423–466, 1988.

  12. EX10 Samad, T., “Towards connectionist rule-based systems,” in Proc. of the IEEE ICNN-88, 2, pp.525–532, 1988.

  13. Barnden, J. A. and Pollack, J. B., Advances in connectionist and neural computation theory, 1, High level connectionist models, Ablex, Norwood, 1991.

  14. Holyoak, K. J. and Barnden J. A., Advances in connectionist and neural computation theory, 2, Analogical connections, Ablex, Norwood, 1994.

  15. Gallant, S. I., Neural network learning and expert systems, MIT Press, Cambridge, 1993.

    MATH  Google Scholar 

  16. Elman, J. L., “Finding structure in time,” Cogn. Sci., 14, pp. 179–211, 1990.

    Article  Google Scholar 

  17. Morita, M., Murata, K. and Morokami, S., “Context-dependent sequential recall by a trajectory attractor network with selective desensitization,” in Proc. of the 3rd ICNNAI, pp. 235–238, 2003.

  18. Morita, M., Matsuzawa, K. and Morokami, S., “A Model of context-dependent association using selective desensitization of nonmonotonic neural elements,” Systems and Computers in Japan, 6, pp. 73–83, 2005.

    Article  Google Scholar 

  19. Morita, M., “Memory and learning of sequential patterns by nonmonotone neural networks”. Neural Netw., 9, pp. 1477–1489, 1996.

    Article  Google Scholar 

  20. Kiani, R., Esteky, H., Mirpour, K. and Tanaka, K., “Object category structure in response patterns of neural population in monkey inferior temporal cortex,” J. Neurophysiol., 97, pp. 4296–4309, 2007.

    Article  Google Scholar 

  21. McCloskey, M. and Cohen, N., “Catastrophic interference in connectionist networks: The sequential learning problem,” The Psychology of Learning and Motivation, 24, pp. 109–164, 1989.

    Article  Google Scholar 

  22. Klar, D., Langley, P. and Neches, R., Production system models of learning and development, MIT Press, Cambridge, 1987.

    Google Scholar 

  23. McDermott, D. and Doyle, J., “Non-monotonic logic I,” Artif. Intell., 13, pp. 41–72, 1980.

    Article  MATH  MathSciNet  Google Scholar 

  24. McCarthy, J., “Circumscription; A form of non-monotonic reasoning,” Artif. Intell., 13, pp. 27–39, 1980.

    Article  MATH  MathSciNet  Google Scholar 

  25. Reiter, R., “A logic for default reasoning,” Artif. Intell., 13, pp. 81–132, 1980.

    Article  MATH  MathSciNet  Google Scholar 

  26. Hanks, S. and McDermott, D., “Default reasoning, non-monotonic logic, and the frame problem,” in Proc. of the AAAI-86, pp. 328–333, 1986.

  27. Suemitsu, A., Miyazawa, Y. and Morita, M., “A model of the activity of the hippocampal neurons based on the theory of selective desensitization,” Neural Information Processing (Part I), LNCS 5506, pp. 383–390, 2009.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ken Yamane.

About this article

Cite this article

Yamane, K., Morita, M. Brain-like Computing Based on Distributed Representations and Neurodynamics. New Gener. Comput. 28, 321–338 (2010). https://doi.org/10.1007/s00354-009-0092-x

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00354-009-0092-x

Keywords

Navigation