NIPS Workshop on Causality: Objectives and Assessment, Whistler 2008

Distinguishing Causes from Effects using Nonlinear Acyclic Causal Models

presenter: Patrik Hoyer, Helsinki Institute for Information Technology
author: Aapo Hyvärinen, University of Helsinki
author: Kun Zhang, Helsinki Institute for Information Technology
published: Dec. 22, 2008, recorded: December 2008, views: 254

Slides

Slides
0:00	Distinguishing Causes from Effects using Nonlinear Acyclic Causal Models
0:24	Outline
1:02	Methods for causal discovery
2:17	Three effects usually encountered in a causal model
3:27	Post-nonlinear (PNL) causal model with inner additive noise
4:24	Three cases of ICA: linear, general nonlinear, and PNL
5:37	PNL mixing ICA: a nice trade-off
6:23	Identifiability of the proposed causal model
7:40	Identification Method
8:26	Special cases
9:29	Experiments
10:23	Results
11:11	Data Set 1
12:41	Data Set 2
13:18	Data Set 3
13:23	Data Set 4
13:24	Data Set 5
13:25	Data Set 6
13:34	Data Set 7
13:36	Data Set 8
13:47	Data Set 7
13:54	Data Set 6
13:59	Data Set 5
14:07	Data Set 4
14:09	Data Set 2
14:10	Data Set 3
14:10	Data Set 4
14:12	Data Set 5
14:13	Data Set 6
14:15	Data Set 7
14:16	Data Set 8
14:17	Conclusion
17:06	- Questions

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.