en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Top-down vs. bottom-up methods for hierarchical classification
Published on Feb 25, 20078343 Views
We deal with hierarchical classification in the general case when an instance could be associated with multiple and/or partial paths in a given taxonomy. We approach the problem from different perspec
Related categories
Chapter list
Top-down vs. bottom-up methods00:01
State of the art:00:38
Hierarchical classi cation model/103:06
Hierarchical classi cation model/206:40
Hierarchical classi cation model/311:45
Hierarchical classi cation model/416:34
Hierarchical classi cation model/418:59
Hierarchical classi cation model/420:00
Hierarchical classi cation model/420:58
B-SVM algorithm (bottom-up)/121:08
B-SVM algorithm (bottom-up)/225:30
B-SVM algorithm (bottom-up)/3:29:44
H-SVM algorithm (top-down) [HCC03,CGZ06], ...30:07
Experimental results/1: Datasets31:36
Experimental results/2: Avg test error (H-loss)34:25
Hierarchical classi cation model/336:05
Experimental results/2: Avg test error (H-loss)36:35
Experimental results/3:37:08
Hierarchical classi cation model/337:35
Experimental results/2: Avg test error (H-loss)38:10
gExperimental results/3:39:15
Experimental results/4: Breakdown on levels40:27
Experimental results/5: Comments40:51
On-line hierarchical classi cation [CGZ06]/141:22
On-line hierarchical classi cation/242:41
On-line hierarchical classi cation/344:02
On-line hierarchical classi cation [CGZ06]/144:12
On-line hierarchical classi cation/344:19
On-line hierarchical classi cation/4: Algorithm/146:08
On-line hierarchical classi cation/4: Algorithm/246:58
On-line hierarchical classi cation/548:21
Conclusions50:50
Open questions51:48
B-SVM algorithm (bottom-up)/156:55
B-SVM algorithm (bottom-up)/201:03:25