HTW Berlin Fotopedia, cc-by-nc, Andrea Kirkby, 2008

HTW Berlin
Fachbereich 4
Internationaler Studiengang
Internationale Medieninformatik (Master)
Semantic Modeling
Summer Term 2016

Tentative Schedule

My schedules are - as always - tentative and subject to change. If you have topics you would like to see addressed - do so at your earliest convienience.

Week
Class Meeting
Thursdays
12.15-13.45
WH C 537
Exercise
due as indicated
Reading Assignment to be done before class
14
07.
04.

Session 1
Introduction to Semantic Modelling and the Semantic Web

Lab 1:
GeoNames

due week 15

Purchase a book on semantic modelling, preferably Semantic Web Programming
15
14.
04.

Session 2
What is the Semantic Web supposed to be? What can I do with it?

Lab 2:
Hello Semantic World Web

due week 17

Read T. Berners-Lee, J. Hendler, and O. Lassila. The Semantic Web. Scientific American 284 (May 2001): 34:43

Will the Semantic Web Change Education?
Kendall Clark, Bijan Parsia, and Jim Hendler

 

16
21.
04.

Session 3
Modelling Information with RDF

 

Read the RDF Primer

17
28.
04.

Session 4
Introduction to Ontologies

Lab 3: RDF

Due week 19

Read A. Johannes Pretorius, Ontologies - Introduction and Overview. From an unpublished Master's Thesis.

Another good source is Natalya F. Noy  and Deborah L. McGuinness, Ontology Development 101: A Guide to Creating Your First Ontology

I've uploaded
Ian Horrocks. 2008. Ontologies and the semantic web. Commun. ACM 51, 12 (December 2008), 58-67. DOI=10.1145/1409360.1409377 http://doi.acm.org/10.1145/1409360.1409377 to the Moodle area!

18
05.
05.
Himmelfahrt    
19 12.
05.

Session 5
Basic OWL


Lab 4: My First Ontology

Due week 21

Browse through W3C Semantic Web & Semanticweb.org

I would be using Allemang & Hendler, Chapter 9, and the nice slides from Antoniou and van Harmelen. I am giving a talk in Leipzig and thus won't be here. You can come to the lab or work with your partner at home, as you wish.

20
19.
05.

Session 6

Counting and sets in OWL

OWL inference

Finding problems in an ontology

 

I will be using
Hebeler Chapter 5

21 26.
05.

Session 7
Logic, Inference, Non-monotonic Reasoning


Lab 5: OWL Pizzeria

Due week 23

Please read Stefan Waner and Steven R. Costenoble. Introduction to Logic, especially chapter 5

Can you do any of these Lewis Carroll puzzles?
22
02.
06.

Session 8

The future of Semantic Web: Intelligent Agents?

 

Read the newest paper from Hendler: Cognitive Extension and the Web

Read a newish paper from Nigel Shadbolt, Wendy Hal and Tim Berners-Lee, Semantic Web Revisited, IEEE Intelligent Systems, 21(3) pp. 96 - 101

Perhaps of interest:
SPARQL for Humanists

23
09.
06.

Session 9

Data Semantics on the Web

Lab 6: Ontology Queries
Due week 25

We will read and discuss Heiner Stuckenschmidt (2012) Data Semantics on the Web. In: J Data Semant 1:1–9, DOI 10.1007/s13740-012-0003-z

 



24
16.
06.

Session 10

Wikidata

  Guest Speaker will be Lydia Pintscher, Product Manager for Wikidata
25
23.
06.

Session 11

Data Mining

Lab 7
Wikidata exercise

Due week 26

Introduction to Data Science, Bill Howe, University of Washington:

Appetite Whetting Part 1
Appetite Whetting Part 2

We will be exploring some simple Data Mining algorithms
26
30.
06.

Session 12

Getting started with Weka

Lab 8: Using Weka

Due week 27

All videos in sessions 12-16 are CC-BY 3.0, Ian Witten

  1. Introduction (9:00)
  2. Exploring the Explorer (11:05)
  3. Exploring datasets (10:37)
  4. Building a classifier (9:00)
  5. Using a filter (7:33)
  6. Visualizing your data (8.37)

 27
07.
07.

Session 13

Evaluation

 

Lab 9:
Classification

Due week 28

Please watch these videos before class!

  1. Be a classifier! (11:18)
  2. Training and testing (5:43)
  3. Repeated training and testing (7:01)
  4. Baseline accuracy (8:00)
  5. Cross-validation (6:54)
  6. Cross-validation results (7:15)
 28
14.
07.

Session 14

Simple classifiers

 

Lab 10:
Nearest neighbor learning

Due week 29

  1. Simplicity first (8:23)
  2. Overfitting (8:36)
  3. Using probabilities (12:31)
  4. Decision trees (9:30)
  5. Pruning decision trees (11:05)
  6. Nearest neighbor (8:42)
29
21.
07.

Session 15

More Classifiers

Lab 11:
Document classification
Due week 30


  1. Classification boundaries (11:48)
  2. Linear regression (9:19)
  3. Classification by regression (10:42)
  4. Logistic regression (10:01)
  5. Support vector machines (8:32)
  6. Ensemble learning (10:00)
30
28.
07.

Session 16

Putting it all together

Summary Discussion
  1. The data mining process (7:41)
  2. Pitfalls and Pratfalls (10:02)
  3. Data mining and ethics (7:43)
  4. Summary (7:30)

 

 


Some rights reserved. CC-BY-NC Prof. Dr. Debora Weber-Wulff
Questions or comments: <weberwu@htw-berlin.de>

Last Change:  2016-06-22 22:06