Perceptual Learning Inspired Model Selection Method of Neural Networks

  • Ziang Lv
  • Siwei Luo
  • Yunhui Liu
  • Yu Zheng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)


Perceptual learning is the improvement in performance on a variety of simple sensory tasks. Current neural network models mostly concerned with bottom-up processes, and do not incorporate top-down information. Model selection is the crux of learning. To obtain good model we must make balance between the goodness of fit and the complexity of the model. Inspired by perceptual learning, we studied on the model selection of neuro-manifold, use the geometrical method. We propose that the Gauss-Kronecker curvature of the statistical manifold is the natural measurement of the nonlinearity of the manifold. This approach provides a clear intuitive understanding of the model complexity.


Perceptual Learning Minimum Description Length Reinforcement Learning Algorithm Statistical Manifold Teaching Signal 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tsodyks, M., Gilbert, C.: Neural Networks and Perceptual Learning. Nature 431, 775–781 (2004)CrossRefGoogle Scholar
  2. 2.
    Gibson, E.J.: Perceptual Learning, Annu. Rev. Psychol. 14, 29–56 (1963)Google Scholar
  3. 3.
    Fahle, M.: Perceptual Learning: Specificity versus generalization. Current Opinion in Neurobiology 15(14), 154–160 (2005)CrossRefGoogle Scholar
  4. 4.
    Tikhonov, A.N.: solution of ill-posed problems. W.H. Winston, Washington (1977)Google Scholar
  5. 5.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1999)Google Scholar
  6. 6.
    Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)MATHCrossRefGoogle Scholar
  7. 7.
    Akaike, H.: Information theory and an extension of the maximum likelihood principle. In: Petrox, B.N., Caski, F. (eds.) Second International Symposium on Information Theory, Budapest, pp. 267–281 (1973)Google Scholar
  8. 8.
    Schwarz, G.: Estimation the dimension of a model. Annals of Statistics 7(2), 461–464 (1978)CrossRefGoogle Scholar
  9. 9.
    Rissanen, J.: Stochastic Complexity and Modeling. Annals of Statistics 14(3), 1080–1100 (1986)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Rissanen, J.: Fisher Information and Stochastic Complexity. IEEE Transaction on Information Theory 42(1), 40–47 (1996)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Amari, S.: Methods of Information Geometry. Oxford University Press, Oxford (2000)MATHGoogle Scholar
  12. 12.
    Santalo, L.A.: Integral Geometry and Geometric Probability. Addison-Wesley, Reading (1979)Google Scholar
  13. 13.
    Spivak, M.: A Comprehensive Introduction to Differential Geometry, vol. 2 of 5 (1979)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ziang Lv
    • 1
  • Siwei Luo
    • 1
  • Yunhui Liu
    • 1
  • Yu Zheng
    • 1
  1. 1.School of Computer and Information TechnologyBeijing Jiaotong UniversityBeijingChina

Personalised recommendations