Perceptual Learning Inspired Model Selection Method of Neural Networks
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.
Unable to display preview. Download preview PDF.
- 2.Gibson, E.J.: Perceptual Learning, Annu. Rev. Psychol. 14, 29–56 (1963)Google Scholar
- 4.Tikhonov, A.N.: solution of ill-posed problems. W.H. Winston, Washington (1977)Google Scholar
- 5.Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1999)Google Scholar
- 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
- 12.Santalo, L.A.: Integral Geometry and Geometric Probability. Addison-Wesley, Reading (1979)Google Scholar
- 13.Spivak, M.: A Comprehensive Introduction to Differential Geometry, vol. 2 of 5 (1979)Google Scholar