The 18th European Conference on Machine Learning (ECML) and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD)

Nonparametric Relational Learning with Applications to Decision Support and Bioinformatics and with a Perspective for the Semantic Web

author: Volker Tresp, Siemens

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Nonparametric Relational Learning with Applications to Decision Support and Bioinformatics and with a Perspective for the Semantic Web
0:28	Relational Representation and Statistical Machine Learning
2:08	I. Relationships are Ubiquitous
2:22	Social Networks
2:41	The WWW is a Relational System
2:58	RDF: the Basis for the Semantic Web
3:19	A Patient is Part of a Relational World
3:43	Relationships are Informative
4:47	Computational Biology
4:59	Relation Extraction from Textual Data
5:27	Cognitive Aspects?
6:06	The John Donne Principle
6:23	John Donne, 1572 – 1631 a Jacobean poet and preacher
6:54	Overview: Learning with Relations (incomplete)
7:55	Some Problems of Previous Work
8:55	This Work
9:29	II. Before Relational Learning
10:00	II.a I.I.D. Learning
10:01	The Matrix
10:34	II.b Towards Relational Learning: Time Series Modelling
10:36	Time Series Models
11:21	II.c Towards Relational Learning: Hierarchical Bayesian Modeling
11:32	Related Tasks
12:14	A Hierarchical Bayesian Model
13:17	Parametric HB is too Stiff!
14:56	A Mixture Model
16:49	Comments
16:53	III Relational Modeling and Learning
17:03	Learning with Relational Data
17:07	Entity Relationship Model
17:54	The Directed Acyclic Probabilistic Entity Relationship (DAPER) Model
18:37	DAPER and Ground Networks
19:24	Structural Learning in Relational Modeling
19:58	IV Infinite Hidden Relational Modeling: Combining Relational Learning with nonparametric Hierarchical Bayes
20:06	Hierarchical Bayes and Relational Learning
21:13	Work on Nonparametric Relational Learning
21:39	Relationship Prediction with Strong Attributes
22:05	Relationship Prediction with Weak (or no) User Attributes: nonparametric Hierarchical Bayes
22:49	Nonparametric Relational Bayes: Infinite Hidden Relational Model
23:21	IHRM with Parameters
23:46	The Recipe
24:43	The Ground Network for the Recommendation System
25:29	Ground Network With an Image Structure
25:46	Ground Network With an Image Structure and Latent Variables: The IHRM
26:18	Advantages of the IHRM (1)
27:02	Advantages of the IHRM (2)
27:39	Scaling of the IHRM
28:00	V Infinite Hidden Relational Modeling: Inference, Learning and Experiments
28:08	Inference in the IHRM
28:55	Technical Details
28:57	Experiment 1: Experimental Analysis on Movie Recommendation
29:03	MovieLens Attributes
29:18	Experimental Analysis on Movie Recommendation NNNN
30:25	Movie cluster analysis Gibbs sampling with CRP (1)
31:46	Movie cluster analysis Gibbs sampling with CRP (2)
32:09	Technical Details
32:18	Empirical Analysis on Bioinformatics (1)
33:09	Empirical Analysis on Bioinformatics (2)
34:27	Empirical Analysis on Bioinformatics (3)
35:39	Relevance of Attributes and Relationships
36:40	Ongoing Work: Integrate Ontology into IHRM (1)
37:47	Ongoing Work: Integrate Ontology into IHRM (2)
38:31	Experiment 3: Experimental Analysis on Clinical Data
39:27	Experimental Analysis on Clinical Data (2)
40:19	Experimental Analysis on Clinical Data (3)
41:16	Conclusion (I)
42:56	VI SML / SRL and the Semantic Web
43:35	Theseus: A Nationally Funded Project for Web 1.0, 2.0, and 3.0
44:43	SW Layers
45:10	XML and RDF
46:17	Ontology
47:03	Logic, Proof, Trust
47:59	Machine Learning and SW
48:10	Machine Learning Classifier
49:13	Does Straightforward Machine Learning Help in Search?
50:12	SW: Classifier (1)
50:55	SW: Classifier (2)
51:55	SW: Search
52:49	(My Current) Conclusion (II)
55:57	- Questions
56:09	- Questions
57:34	- Questions
61:04	- Questions
61:59	- 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.