n-free test-set 0.65 0.738 0.825 0.913 1 0.2 0.4 0.8 0.2 0.4 0.8 0.2 0.4 0.8 Accuracy -0.04 -0.03 -0.02 -0.01 0 0.01 0.02 0.2 0.4 0.8 0.2 0.4 0.8 0.2 0.4 0.8 Discrimination Naive Bayes 2 NB Models Expectation [...] Maximization EM with prior 0 0.001 0.002 0.002 0.003 0.2 0.4 0.8 0.2 0.4 0.8 0.2 0.4 0.8 Discrimination Variances 0.2 0.4 0.8 0.2 0.4 0.8 0.2 0.4 0.8 Fig. 3 The results of Fig. 2 (accuracy, discrimination [...] Modifying naive Bayes 3.2 Two naive Bayes models 3.3 A latent variable model 4 Finding the latent values 4.1 Expectation maximization 4.2 Using prior knowledge 5 Experiments 5.1 Tests on artificial data 5.1 …

untitled

ne spectral pro- jected gradient methods on convex sets,” SIAM J. Optim., vol. 10, no. 4, pp. 1196–1211, 2000. [4] T. Blumensath and M. Davies, “Gradient pursuits,” IEEE Trans. Signal Process., 2008, submitted [...] “Signal recovery by proximal forward- backward splitting,” SIAM J. Multiscale Model. Simul., vol. 4, no. 4, pp. 1168–1200, 2005. [18] Y.-H. Dai and R. Fletcher, “Projected Barzilai-Borwein methods for l [...] garrote,” J. Comput. Graph. Stat., vol. 7, no. 4, pp. 469–488, 1998. [44] H. Gao and A. Bruce, “Waveshrink with firm shrinkage,” Statistica Sinica, vol. 7, no. 4, pp. 855–874, Oct. 1997. [45] D. Goldfarb and …

Microsoft Word - Schoen03-08proof.doc

percentage of Ki-67 positive nuclei was 1.52 ± 1.17, 3.50 ± 0.98 and 4.30 ± 1.96 % in groups 1, 2 and 3, respectively (Fig. 4A and 4B). Thus, topical administration of EPO alone (group 2) caused a 2.3-fold [...] group 1 group 2 group 3 po s. H ep at oc yt es (% ) 0 1 2 3 4 Ki-67 day 14 group 1 group 2 group 3 po s. H ep at oc yt es (% ) 0 2 4 6 8 * * Figure 4.A: Effect of EPO on proliferation of hepatocytes as evidenced [...] group 3 qu ot ie nt e ry th ro po ie si s/ m ye ol op oi es is C D 1 17 p os .c el ls 0,2 0,4 0,6 0,8 1,2 1,4 1,6 1,8 0,0 1,0 2,0 * Figure 5: CD 117 staining of bone marrow on day 14 after liver resection …