event thumbnail image
Machine Learning Summer School 2005 - Chicago
Pascal

Generalization bounds

author: John Langford, Yahoo Research, Yahoo!

Description

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 we make only an assumption that all examples are drawn independently and identically from some (unknown) distribution, we can answer the question. The answer to this question is directly applicable to classifier testing and confidence reporting. It also provides a simple general explanation of "overfitting", and influences algorithm design.

You might be experiencing some problems with Your Video player.
Slides
0:01 Practical generalization Bounds
1:03 Learning
3:45 Why study ..
4:33 Better Methods ...
5:41 To gain ...
6:33 Outline
7:22 Model: Definitions
8:37 Model:Derived quantities
9:14 Model:Derived quantities
10:33 Model:Basic Observations
11:15 Possible Error distributions
12:30 Model:basic quantities
13:30 Model:basic quantities
15:14 Outline
15:26 test Set Bound
15:52 test Set Bound
20:18 Observation and
21:03 Observation and
21:28 True Error Bound
21:39 Test Set...
22:19 What does Test...
26:09 Test Set...
31:06 Test Set...
31:40 True error
34:40 Test Set...
34:50 Interpretation
36:14 K-fold
41:21 outline
41:54 Trainig Set...
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`s Razor...
51:45 Occam Bound...
52:01 True Error...
53:35 Occam`s Razor...
54:17 Occam`s Razor...
55:33 test Set...

Lecture rating

People found this lecture:
Worth seeing
because it is:
 Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:03:06
Slide Synchronization Windows Media video

!NOW PLAYING
Watch Part 2
Part 2 0:39:30
Slide Synchronization Windows Media video

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment: