Figure 1: Projection view of the Li data model (6.3) with different
rotations: (a) best view of the data, (b) SIR, (c) KPCA, and (d) KSIR.
Gaussian kernel with scale of 0.05 is used.
¡@
(a) The raw data (x1&x2).
¡@
(b) PCA.
(b) KPCA.
(b) SIR.
(b) KSIR.
Figure 2: The 3D animations for the response y against the first 2 dimension
reduction projections.
¡@
¡@
Wu, H. M.* (2008). Kernel Sliced Inverse
Regression with Applications to Classification, Journal of
Computational and Graphical Statistics. 17(3), 590-610.
http://www.hmwu.idv.tw/KSIR
Last updated:
2009/04/27