Study unit
3621687 Local Patterns in Data, 5 Cp  
Code 3621687  Validity 01.01.1950 -
Name Local Patterns in Data  Abbreviation LPD 
Credits 5 Cp Date of expiry  
TypeAdvanced Studies Subject0530 Computer Science 
ClassStudy Unit  Hours  
Study right   Grading0-5 
Recommended scheduling 
   
Organisation Computer Science (J,K) 

Description
Learning outcomes 

The student knows about different data mining methods for finding local patterns in data, their purpose and their limitations, and understands the similarities and differences between the approaches.

The student knows about tools for dealing with redundancy and pattern significance, and approaches for modelling the user's interest.

The student is able to identify techniques from the literature and adapt them to an exploratory data-analysis scenario at hand

The aim of the course is two-fold.

On one hand, the students will learn about pattern mining, from the standard frequent itemset mining task and including related techniques and problem variants which can be used for data analysis.

 On the other hand, the students will train their scientific reading and writing skills. That is, the course will be an opportunity for students to practise critical reading of scientific literature, understanding and summarizing as most of the work during the course will consist in reading and reporting on selected research articles.

 
Content 

Frequent and contrasting pattern mining, Subgroup Discovery, Exceptional Model Mining, Redescription mining.

 

Pattern set mining, Preference-based and constraint-based pattern mining, skypatterns

Randomization tests, Minimum Description Length, Maximum Entropy, Subjective Interestingness

 
Modes of study 

Lectures, essay writing, and solving programming assignments in Python, exam

 
Teaching methods 

Contact teaching 46 h (incl. lectures, exercises, and oral presentations)

 
Study materials 

A selected corpus of research papers

 
Evaluation criteria 

Grading: 0–5, based on exam, essays and assignments

 
Prerequisites 

Algorithmic Data Analysis (or equivalent knowledge).

 


Letter (J, K) in front of the name of the course/exam indicates the campus on which teaching or exam takes place: J = Joensuu, K = Kuopio.

Present and future teaching
No teaching

Future exams
Functions Name Type Cp Teacher Timetable
Registration not started (JOENSUU): Local Patterns in Data  General examination  Esther Galbrun 
20.08.20thu 12.00-16.00
Registration not started (KUOPIO): Local Patterns in Data  General examination  Esther Galbrun 
20.08.20thu 12.00-16.00