en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Generalization bounds
Published on Feb 25, 20078643 Views
When a learning algorithm produces a classifier, a natural question to ask is "How well will it do in the future?" To make statements about the future given the past, some assumption must be made. If
Related categories
Chapter list
Practical generalization Bounds00:01
Learning01:03
Why study ..03:45
Better Methods ...04:33
To gain ...05:41
Outline06:33
Model: Definitions07:22
Model:Derived quantities08:37
Model:Derived quantities09:14
Model:Basic Observations10:33
Possible Error distributions11:15
Model:basic quantities12:30
Model:basic quantities13:30
Outline15:14
test Set Bound15:26
test Set Bound15:52
Observation and20:18
Observation and21:03
True Error Bound21:28
Test Set...21:39
What does Test...22:19
Test Set...26:09
Test Set...31:06
True error31:40
Test Set...34:40
Interpretation34:50
K-fold36:14
outline41:21
Trainig Set...41:54
Occam`s Razor...45:11
Occam`s Razor...46:21
Occam`s Razor...48:28
Occam`s Razor...49:01
Occam`s Razor...49:21
Occam`s Razor...50:46
Occam`s Razor...51:02
Occam Bound...51:45
True Error...52:01
Occam`s Razor...53:35
Occam`s Razor...54:17
test Set...55:33