Knowledge Discovery in extensive data sets

author: Dunja Mladenić, Jožef Stefan Institute

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Knowledge Discovery in extensive data sets
0:17	Outline
1:27	Knowledge Discovery in Databases (1)
1:29	Knowledge Discovery in Databases (2)
2:43	What is Knowledge Discovery in Databases?
3:37	Knowledge Discovery Process
4:05	Basic Steps of KDD
4:58	Main Approaches
7:20	Example Tasks of classification/prediction
7:53	Recommending News Articles
8:22	Supervised learning
9:18	Algorithms for learning classification models
9:32	Nearest neighbor
9:46	Similarity/Distance
9:51	Nearest neighbor
10:36	Semi-supervised learning
11:19	Using unlabeled data (Nigam et al., 2000)
11:44	Using Unlabeled Data with Expectation-Maximization (EM)
12:24	Co-training (Blum & Mitchell, 1998)
12:37	Bootstrap Learning to Classify Web Pages
14:03	Active Learning
15:13	Approaches to Active Learning (1)
15:19	Approaches to Active Learning (2)
16:54	Text-Mining
19:59	What is Text-Mining?
20:34	Why dealing with Text is Tough? (M.Hearst 97)
21:12	Why dealing with Text is Easy? (M.Hearst 97)
21:38	Who is in the text analysis arena?
22:22	What dimensions are in text analytics?
22:46	How dimensions fit to research areas?
22:58	Levels of text representations
23:59	Text-Garden –software tools for text-mining and semantic-web
25:26	What is Text-Garden?
26:08	Some history…
26:40	…local development of Text-Garden
27:00	Functionality blocks
27:57	Technical aspects
28:12	Multiplatform Text-Garden
28:20	Availability
28:27	Text Visualization(Document-Atlas http://docatlas.ijs.si)
28:47	Visualization in DocumentAtlas(developed on the top of Text Garden)
30:03	Approach Description
30:52	Document Atlas –visualization of document collections and their structure
33:08	Web-search visualization(http://searchpoint.ijs.si)
33:11	Visualization of search results(developed on the top of Text Garden)
34:05	Approach Description
34:15	Example: A4
37:00	Example: Password (1)
37:52	Example: Password (2)
39:35	Example: Password (3)
42:21	Summarization of documents through semantic-graphs
43:26	Approach Description
43:55	Summarization
44:18	Example of summarization
44:39	Automatically generated graph of summary triples
45:30	Ontology Learning with OntoGen (http://ontogen.ijs.si)
45:55	Ontology Learning with OntoGen(developed on the top of Text Garden)
47:12	Basic idea behind OntoGen
47:33	Ontology generation from scratch (1)
47:57	Ontology generation from scratch (2)
48:56	Ontology generation from scratch (3)
49:04	Ontology generation from scratch (4)
49:20	Ontology generation from scratch (5)
49:36	Ontology generation from scratch (6)
49:43	Ontology generation from scratch (7)
49:46	Ontology generation from scratch (8)
50:00	Contextualized ontology generation
50:22	Examples of Real-world Ontologies
51:04	Term mapping in ontologies
51:07	Term Matching of two ontologies (developed on the top of Text Garden)
52:07	Example (1)
52:12	Example (2)
52:23	Software Mining (developed on the top of Text Garden)
53:04	Extracting data (1)
53:22	Extracting data (2)
53:40	Extracting data (3)
54:08	Example graph
54:19	Example graph -zoomed
54:27	Structuring extracted knowledge
54:43	Alarms Explorer project
56:04	What is Alarms Explorer
57:55	Back-end
59:01	Alarms Explorer interface
59:35	Statistics
59:51	Predictions
60:23	Long term trends
60:29	Hardware requirements
61:38	Deep-semantics with Cyc
62:08	Cyc …a little bit of historical context
63:18	The Cyc Ontology
63:38	Structure of Cyc Ontology
63:49	Cyc’s front-end: “Cyc Analytic Environment” –querying (1/2)
64:42	Cyc k-base related to transport (1)
65:07	Cyc k-base related to transport (2)
65:48	Oil consumption prediction and oil distribution optimization
66:15	The problem case
67:04	Solution
67:37	Structure of the complete solution
67:40	Results
68:42	Analysing European science¸(http://www.ist-world.org)
69:22	The problem case
70:31	Data
70:58	Results
72:11	Current visitors statistics
73:16	Our group

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.