9th International Colloquium on Grammatical Inference

Relevant representations for the inference of rational stochastic tree languages

author:Amaury Habrard, University of Provence
published: Oct. 9, 2008, recorded: September 2008, views: 28

You might be experiencing some problems with Your Video player.

Slides

Slides
0:00	Relevant Representations for the Inference of Rational Stochastic Tree Languages
0:55	Outline
2:07	Outline - The Basic Problem
2:08	Trees
2:29	Stochastic Tree Languages
3:24	A Basic Problem in Probabilistic Grammatical Inference
3:43	Probabilistic Tree Automata
5:01	Linear Representations of Rational Tree Languages
6:56	Rational Stochastic Tree Languages
7:50	Outline - A Canonical Linear Representation for Rational Tree Series
7:55	Word Languages: The Notion of Residual Languages
8:40	Contexts
9:07	An Algebraic Characterization of Rational Series
9:48	The Canonical Linear Representation of Rational Series - 1
10:04	The Canonical Linear Representation of Rational Series - 2
10:26	The Canonical Linear Representation of Rational Series - 3
10:31	The Canonical Linear Representation of Rational Series - 4
10:53	Building the Canonical Linear Representation - 1
10:57	Building the Canonical Linear Representation - 2
11:17	Building the Canonical Linear Representation - 3
11:28	Building the Canonical Linear Representation - 4
11:42	Building the Canonical Linear Representation - 5
11:54	Building the Canonical Linear Representation - 6
12:13	Building the Canonical Linear Representation - 7
12:39	Building the Canonical Linear Representation - 8
12:46	Building the Canonical Linear Representation - 9
13:07	Building the Canonical Linear Representation - 10
13:12	Building the Canonical Linear Representation - 11
13:15	Building the Canonical Linear Representation - 12
13:16	Building the Canonical Linear Representation - 13
13:28	Building the Canonical Linear Representation - 14
14:02	Algorithm DEES; Independence Test
15:00	Properties of DEES
15:37	Outline - Contributions
15:39	The Normalization of the Model - 1
16:18	The Normalization of the Model - 2
16:34	After Renormalization
17:35	Notion of Strong Consistency
18:28	Adapting the Framework to Unranked Trees
19:45	Conclusion: Learning RSTL from i.i.d. Samples
21:47	- Questions
22:40	- Questions
23:31	- Questions
25:12	- Questions
25:24	- Questions
25:56	- Questions

Related content

Visitors who watched this lecture also watched...