Relations between machine learning problems – an approach to unify the field

Relations Betweeen Machine Learning Problems

author: Robert C. Williamson, Australian National University
published: Jan. 25, 2012, recorded: December 2011, views: 1739

Slides

Slides
0:00	Relations Betweeen Machine Learning Problems
0:05	Why this workshop? - 1
0:23	Why this workshop? - 2
0:32	Why this workshop? - 3
0:43	Why this workshop? - 4
1:51	Analogy - 1
2:23	Analogy - 2
2:34	The 20th Century View. . .
3:11	(One possible) Goal - 1
3:21	(One possible) Goal - 2
3:39	Why “relations” rather than “attributes”? - 1
4:09	Why “relations” rather than “attributes”? - 2
4:47	Why “relations” rather than “attributes”? - 3
4:57	Grothendieck’s Relative Point of View
5:49	Why “problems” and not “algorithms”
7:32	Problem oriented versus method oriented - 1
8:13	Problem oriented versus method oriented - 2
8:23	Problem oriented versus method oriented - 3
8:36	A flood of problems - 1
8:56	A flood of problems - 2
9:39	Studying relations between ML problems is not new. . .
10:14	Lots of Existing Relations - 1
10:38	Lots of Existing Relations - 2
11:04	Lots of Existing Relations - 3
11:26	Lots of Existing Relations - 4
12:51	Lots of Existing Relations - 5
13:26	Not just “reductions”
14:11	Types of Relations
14:47	Monocausotaxophilia considered harmful - 1
14:59	Monocausotaxophilia considered harmful - 2
16:48	Standards and Modularisation
19:32	Not just a theoretical exercise! - 1
19:41	Not just a theoretical exercise! - 2
20:05	Not just a theoretical exercise! - 3
20:09	Not just a theoretical exercise! - 4
20:17	Not just a theoretical exercise! - 5
20:30	Not just a theoretical exercise! - 6
20:32	Desired Outcomes - 1
21:01	Desired Outcomes - 2
22:04	Desired Outcomes - 3
22:17	Desired Outcomes - 4
23:08	Desired Outcomes - 5
23:10	Desired Outcomes - 6

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.

Lecture popularity: You need to login to cast your vote.