en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Learning from Labeled and Unlabelled Data: When the Smoothness Assumption Holds
Published on Mar 11, 20114795 Views
During recent years, there has been a growing interest in learning algorithms capable of utilizing both labeled and unlabeled data for prediction tasks. The reason for this attention is the cost of
Related categories
Chapter list
Learning from Labeled and Unlabelled Data: When the Smoothness Assumption Holds00:00
Transductive/semi-supervised vs Inductive Learning in predictive tasks (1)02:54
Transductive/semi-supervised vs Inductive Learning in predictive tasks (2)03:42
Motivation for Transductive/Semi- Supervised Learning (1)05:10
Motivation for Transductive/Semi- Supervised Learning (2)05:18
Transductive vs Semi-supervised learning: differences (1)06:29
Transductive vs Semi-supervised learning: differences (2)07:39
Transductive vs Semi-supervised learning: differences (3)08:26
Transductive learning vs. inductive learning vs. semi-supervised learning09:32
Transductive learning: early references10:11
Smoothness assumption in supervised learning11:30
Semi-supervised smoothness assumption (1)13:01
Semi-supervised smoothness assumption (2)13:45
Semi-supervised smoothness assumption (3)14:47
Cluster assumption15:28
Transductive learning: which assumptions16:15
Transductive learning vs. local learning16:34
Autocorrelation17:44
Positive Autocorrelation19:20
Positive autocorrelation and the smootness assumption (1)20:03
Positive autocorrelation and the smootness assumption (2)21:14
Spatial Data22:37
Networked Data23:27
Opportunities for Transductive learning23:58
HSGT: Hierarchical classification of textual documents24:56
HSGT in WebClass: the problem25:00
HSGT in WebClass: basic idea26:09
HSGT in WebClass: the problem (1)27:48
Document representation29:35
HSGT in WebClass: the problem (2)30:23
HSGT in WebClass: the problem (3)30:55
Relevant Example Selection31:40
Experiments32:37
Some Experimental Results33:50
SPRECO (SPatial REgression with CO-training)34:26
Transductive Spatial Regression (1)34:36
Transductive Spatial Regression (2)35:27
The solution: SPatial REgression with CO-training (1)35:47
The solution: SPatial REgression with CO-training (2)36:09
Two Views of Spatial Data37:19
Determine reliability of labels (1)38:07
Determine reliability of labels (2)39:55
Labeling40:40
Experiments (1)42:05
Experiments (2)42:34
TRANSC (TRANsductive Structural Classifier) (1)43:01
TRANSC (TRANsductive Structural Classifier) (2)43:05
TRANSC: problem definition46:55
TRANSC: algorithm48:34
TRANSC (1)50:05
TRANSC (2)50:18
TRANSC (3)50:57
North-West England Census Data (1)51:06
North-West England Census Data (2)52:13
Munich Census Data (1)52:49
Munich Census Data (2)53:32
Thanks53:51