Download Review List for the 2013 Data Mining Final Exam

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Nonlinear dimensionality reduction wikipedia , lookup

Expectation–maximization algorithm wikipedia , lookup

Nearest-neighbor chain algorithm wikipedia , lookup

K-nearest neighbors algorithm wikipedia , lookup

K-means clustering wikipedia , lookup

Cluster analysis wikipedia , lookup

Transcript
COSC 6335 “Data Mining”
Review Sheet for 2013 Final Exam COSC 6335
The final exam has been scheduled for Tu., December 17, 11a-1:10p in T101 and will
be “open everything” and will take 120 minutes. The use of computers is not allowed!
The exam counts approx. 32% towards the final course grade. The exam will cover the
following topics:
1. ****** Classification Techniques (no ensembles, no ROC curves)
a. all transparencies covered in the lecture in part2 of classification and
transparencies which cover decision tree induction and model
evaluation (note that several transparencies cover material that is not
discussed in the book)
b. book pages: 147-162 172-183 186-188 223-227, 256-274,
c. discussion of kNN in the Top 10 Data Mining Algorithm paper
2. ****** Clustering (no DBSCAN, no cluster evaluation)
a. Algorithms: Overview Clustering, K-means, Hierarchical Clustering,
DENCLUE
c. Book pages: 491-508, 515-522, 524-526, 608-612
d. All transparencies associated with topics listed in a
e. Discussion of K-means in the Top 10 Data Mining Algorithm paper
3. ***** Association Analysis
a. book pages: 327-341, 349-353, 415-422, 429-435 and all transparencies
that are associated with those book pages
5. *Spatial Data Mining
a. Read http://en.wikipedia.org/wiki/Spatial_analysis
b. Transparencies of the Introduction to Spatial Data Mining
6. ** PageRank
a. Class transparencies excluding Gleich Dissertation transparencies
b. Wikipedia PageRank page
c. Discussion of PageRank in the Top 10 Data Mining Algorithm paper
7. ** Introduction to Data Mining
a. Transparencies covered in the first week of the semester
b. Textbook pages 1-12
8. *** Most likely there will be an essay-style question in the exam, related to a
single or multiple topics listed above.
Algorithms and techniques you should know well include: kNN, SVM, K-means,
decision tree induction algorithm, hierarchical clustering algorithms, DENCLUE,
APRIORI, generalization of APRIORI for sequence mining, PageRank algorithm.
1