Modelling in Classification and Statistical Learning Workshop

How classifieres can be use to solve any reasonable loss

author: John Langford, Yahoo! Research

You might be experiencing some problems with Your Video player.

*Slides*
0:02	How Classifiers can be ...
0:27	A Machine Learning Dream
3:14	Two Versions of the Dream
4:57	Basic Question
6:14	The Reductionist Style for ...
8:27	Defining the Learning Problem
15:36	Step (1) Class Probability Estimation
17:00	Step (2) The Probing Method: Observations
21:47	The Probing Algorithm
23:27	Step (2) The Probing Method: Detailes
27:23	Step (3) The one classifier trick
32:11	Step (3) Probing Theory
51:44	What Are Learning Reductions?
52:39	Disadvantages of Learning Reductions
54:09	Error Limiting Reductions
57:13	Uses of Error Limiting Reductions
57:17	Regret Transform Reductions
58:13	Uses of Regret Transform Reductions
58:18	Big Questions

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.