cg

diff grant.html @ 66:f14c34563ff8

.
author bshanks@bshanks.dyndns.org
date Mon Apr 20 13:08:18 2009 -0700 (16 years ago)
parents f1f92feb3230
children 20e4b29ddc99
line diff
1.1 --- a/grant.html Sun Apr 19 16:24:10 2009 -0700 1.2 +++ b/grant.html Mon Apr 20 13:08:18 2009 -0700 1.3 @@ -468,6 +468,12 @@ 1.4 Gene mtif2 is shown in the upper-right. Mtif2 captures MO’s upper-left boundary, but not its lower-right boundary. Mtif2 1.5 does not express very much on the medial surface. By adding together the values at each pixel in these two figures, we get 1.6 the lower-left image. This combination captures area MO much better than any single gene. 1.7 + 1.8 + 1.9 + 1.10 + 1.11 + 1.12 + Figure 6: todo liso 1.13 surface pixels based on their gene expression profiles. We achieved classification accuracy of about 81%19. As noted above, 1.14 however, a classifier that looks at all the genes at once isn’t as practically useful as a classifier that uses only a few genes. 1.15 Data-driven redrawing of the cortical map 1.16 @@ -539,6 +545,8 @@ 1.17 # confirm with EMAGE, GeneAtlas, GENSAT, etc, to fight overfitting 1.18 # compare using clustering scores 1.19 # multivariate gradient similarity 1.20 +# deep belief nets 1.21 +# note: slice artifact 1.22 Bibliography & References Cited 1.23 [1]Tanya Barrett, Dennis B. Troup, Stephen E. Wilhite, Pierre Ledoux, Dmitry Rudnev, Carlos Evangelista, Irene F. 1.24 Kim, Alexandra Soboleva, Maxim Tomashevsky, and Ron Edgar. NCBI GEO: mining tens of millions of expression