Subject description - A4M33SAD

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
A4M33SAD Machine Learning and Data Analysis
Roles:  Extent of teaching:2P+2C
Department:13136 Language of teaching:CS
Guarantors:  Completion:Z,ZK
Lecturers:  Credits:6
Tutors:  Semester:Z

Web page:

http://cw.felk.cvut.cz/doku.php/courses/a4m33sad/start

Anotation:

The course explains machine learning methods helpful for getting insight into data by automatically discovering interpretable data models such as graph- and rule-based. The course will also address a theoretical framework explaining why/when the explained algorithms can in principle be expected to work. The lectures are given in English.

Study targets:

Learn principles of selected methods of data analysis methods and classifier learning, and elements of learning theory.

Course outlines:

1. Course introduction. Cluster analysis -- foundations (k-means, hierarchical and EM clustering).
2. Cluster analysis -- advanced methods (spectral clustering).
3. Cluster analysis -- special methods (conceptual and semi-supervised clustering, co-clustering).
4. Frequent itemset mining. the Apriori algorithm, association rules.
5. Frequent sequence mining. Episode rules. Sequence models.
6. Frequent subtrees and subgraphs.
7. Dimensionality reduction.
8. Computational learning theory - intro, PAC learning.
9. Computational learning theory (cont'd).
10. PAC-learning logic forms.
11. Learning in predicate logic.
12. Infinite Concept Spaces.
13. Empirical testing of hypotheses.
14. Wrapping up (if 14 lectures).

Exercises outline:

1. Entry test (prerequisite course RPZ). SW tools for machine learning (RapidMiner, WEKA).
2. Data preprocessing, missing and outlying values, clustering.
3. Hierarchical clustering, principal component analysis.
4. Spectral cluestering.
5. Frequent itemset mining, association rules
6. Frequent sequence/subgraph mining.
7. Test (first half of the course). Learning Curve.
8. Underfitting and overfitting, ensemble classification, error estimates, cross-validation.
9. Model selection and assessment, ROC analysis.
10. Project work.
11. Project work.
12. Inductive logic programming: the Aleph system.
13. Statistical relational learning: the Alchemy system.
14. Credits.

Literature:

T. Mitchell: Machine Learning, McGraw Hill, 1997
P. Langley: Elements of Machine Learning, Morgan Kaufman 1996
T. Hastie et al: The elements of Statistical Learning, Springer 2001

Requirements:

Topics contained in course A4B33RPZ. For details see http://cw.felk.cvut.cz/doku.php/courses/m33sad/start

Keywords:

clustering, frequent patterns, classifier, PAC-learning

Subject is included into these academic programs:

Program Branch Role Recommended semester


Page updated 28.3.2024 09:54:15, semester: Z,L/2023-4, Z/2024-5, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)