Advertisement

Brain Like Temporal Processing

  • Juyang Weng
Part of the Studies in Computational Intelligence book series (SCI, volume 355)

Abstract

This chapter presents a general purpose model of the brain, called Developmental Networks (DN). Rooted in the biological genomic equivalence principle, our model proposes a general-purpose cell-centered in-place learning scheme to handle all levels of brain development and operation, from the cell level all the way to the brain level. It clarifies five necessary “chunks” of the brain “puzzle”: development, architecture, area, space and time. Then, this chapter analyzes how such a model enables a developmental robot to deal with temporal contexts. It deals with temporal context of any length without a dedicated temporal component.

Keywords

Simple Complex Mental Development Temporal Context Complex Background Lateral Excitation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Albus, J.S.: Outline for a theory of intelligence. IEEE Trans. Systems, Man and Cybernetics 21(3), 473–509 (1991)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Albus, J.S.: A model of computation and representation in the brain. Information Science 180(9), 1519–1554 (2010)CrossRefGoogle Scholar
  3. 3.
    Callaway, E.M.: Feedforward, feedback and inhibitory connections in primate visual cortex. Neural Networks 17, 625–632 (2004)zbMATHCrossRefGoogle Scholar
  4. 4.
    Elman, J.L., Bates, E.A., Johnson, M.H., Karmiloff-Smith, A., Parisi, D., Plunkett, K.: Rethinking Innateness: A connectionist perspective on development. MIT Press, Cambridge (1997)Google Scholar
  5. 5.
    Emami, A., Jelinek, F.: A neural syntactic language model. Machine Learning 60, 195–227 (2005)CrossRefGoogle Scholar
  6. 6.
    George, D., Hawkins, J.: Towards a mathematical theory of cortical micro-circuits. PLoS Computational Biology 5(10), 1–26 (2009)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Hecht-Nielsen, R.: Confabulation Theory. Springer, Berlin (2007)Google Scholar
  8. 8.
    Jelinek, F.: Self-organized language modeling for speech recognition. In: Waibel, A., Lee, K. (eds.) Readings in Speech Recognition, pp. 450–506. Morgan Kaufmann, San Mateo (1990)Google Scholar
  9. 9.
    Lee, T.S., Mumford, D.: Hierarchical bayesian inference in the visual cortex. J. Opt. Soc. Am. A 20(7), 1434–1448 (2003)CrossRefGoogle Scholar
  10. 10.
    Luciw, M., Weng, J.: Where What Network 3: Developmental top-down attention with multiple meaningful foregrounds. In: Proc. IEEE International Joint Conference on Neural Networks, Barcelona, Spain, July 18-23, pp. 4233–4240 (2010)Google Scholar
  11. 11.
    Luciw, M., Weng, J., Zeng, S.: Motor initiated expectation through top-down connections as abstract context in a physical world. In: IEEE International Conference on Development and Learning, August 9-12, Monterey, CA, pp. +1–6. (2008)Google Scholar
  12. 12.
    Miyan, K., Weng, J.: WWN-Text: Cortex-like language acquisition with What and Where. In: Proc. IEEE 9th International Conference on Development and Learning, Ann Arbor, August 18-21, pp. 280–285 (2010)Google Scholar
  13. 13.
    Piaget, J.: The Construction of Reality in the Child. Basic Books, New York (1954)Google Scholar
  14. 14.
    Purves, W.K., Sadava, D., Orians, G.H., Heller, H.C.: Life: The Science of Biology, 7th edn. Sinauer, Sunderland, MA (2004)Google Scholar
  15. 15.
    Solgi, M., Weng, J.: Developmental stereo: Emergence of disparity preference in models of visual cortex. IEEE Trans. Autonomous Mental Development 1(4), 238–252 (2009)CrossRefGoogle Scholar
  16. 16.
    Tenenbaum, J.B., Griffithsb, T.L., Kemp, C.: Theory-based bayesian models of inductive learning and reasoning. Trends in Cognitive Sciences 10(7), 309–318 (2006)CrossRefGoogle Scholar
  17. 17.
    Weng, J.: Task muddiness, intelligence metrics, and the necessity of autonomous mental development. Minds and Machines 19(1), 93–115 (2009)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Weng, J.: A 5-chunk developmental brain-mind network model for multiple events in complex backgrounds. In: Proc. Int’l Joint Conf. Neural Networks, Barcelona, Spain, July 18-23, pp. 1–8 (2010)Google Scholar
  19. 19.
    Weng, J., Ahuja, N., Huang, T.S.: Learning recognition and segmentation of 3-D objects from 2-D images. In: Proc. IEEE 4th Int’l Conf. Computer Vision, pp. 121–128 (May 1993)Google Scholar
  20. 20.
    Weng, J., Ahuja, N., Huang, T.S.: Learning recognition and segmentation using the Cresceptron. International Journal of Computer Vision 25(2), 109–143 (1997)CrossRefGoogle Scholar
  21. 21.
    Weng, J., Luciw, M.: Dually optimal neuronal layers: Lobe component analysis. IEEE Trans. Autonomous Mental Development 1(1), 68–85 (2009)CrossRefGoogle Scholar
  22. 22.
    Weng, J., McClelland, J., Pentland, A., Sporns, O., Stockman, I., Sur, M., Thelen, E.: Autonomous mental development by robots and animals. Science 291(5504), 599–600 (2001)CrossRefGoogle Scholar
  23. 23.
    Weng, J., Zhang, Q., Chi, M., Xue, X.: Complex text processing by the temporal context machines. In: Proc. IEEE 8th International Conference on Development and Learning, Shanghai, China, June 4-7, pp. +1–8 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Juyang Weng
    • 1
  1. 1.Michigan State UniversityEast LansingUSA

Personalised recommendations